forked from Karylab-cklius/vllm
Compare commits
4
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 Zhuohan Li
|
d5bf492f16 | ||
|
Zhuohan Li
|
8c7bab79f5 | ||
|
Zhuohan Li
|
1936d7bab0 | ||
|
Zhuohan Li
|
996cf2de5c |
@@ -1,53 +1,36 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import os
|
||||
import sys
|
||||
import zipfile
|
||||
|
||||
# Read the VLLM_MAX_SIZE_MB environment variable, defaulting to 500 MiB
|
||||
# Note that we have 800 MiB quota, please use it wisely.
|
||||
# See https://github.com/pypi/support/issues/6326 .
|
||||
# Please also sync the value with the one in Dockerfile.
|
||||
VLLM_MAX_SIZE_MB = int(os.environ.get("VLLM_MAX_SIZE_MB", 500))
|
||||
MAX_SIZE_MB = 200
|
||||
|
||||
|
||||
def print_top_10_largest_files(zip_file):
|
||||
"""Print the top 10 largest files in the given zip file."""
|
||||
with zipfile.ZipFile(zip_file, "r") as z:
|
||||
with zipfile.ZipFile(zip_file, 'r') as z:
|
||||
file_sizes = [(f, z.getinfo(f).file_size) for f in z.namelist()]
|
||||
file_sizes.sort(key=lambda x: x[1], reverse=True)
|
||||
for f, size in file_sizes[:10]:
|
||||
print(f"{f}: {size / (1024 * 1024):.2f} MBs uncompressed.")
|
||||
print(f"{f}: {size/(1024*1024)} MBs uncompressed.")
|
||||
|
||||
|
||||
def check_wheel_size(directory):
|
||||
"""Check the size of .whl files in the given directory."""
|
||||
for root, _, files in os.walk(directory):
|
||||
for file_name in files:
|
||||
if file_name.endswith(".whl"):
|
||||
wheel_path = os.path.join(root, file_name)
|
||||
wheel_size_mb = os.path.getsize(wheel_path) / (1024 * 1024)
|
||||
if wheel_size_mb > VLLM_MAX_SIZE_MB:
|
||||
for f in files:
|
||||
if f.endswith(".whl"):
|
||||
wheel_path = os.path.join(root, f)
|
||||
wheel_size = os.path.getsize(wheel_path)
|
||||
wheel_size_mb = wheel_size / (1024 * 1024)
|
||||
if wheel_size_mb > MAX_SIZE_MB:
|
||||
print(
|
||||
f"Not allowed: Wheel {wheel_path} is larger "
|
||||
f"({wheel_size_mb:.2f} MB) than the limit "
|
||||
f"({VLLM_MAX_SIZE_MB} MB)."
|
||||
)
|
||||
f"Wheel {wheel_path} is too large ({wheel_size_mb} MB) "
|
||||
f"compare to the allowed size ({MAX_SIZE_MB} MB).")
|
||||
print_top_10_largest_files(wheel_path)
|
||||
return 1
|
||||
else:
|
||||
print(
|
||||
f"Wheel {wheel_path} is within the allowed size "
|
||||
f"({wheel_size_mb:.2f} MB)."
|
||||
)
|
||||
print(f"Wheel {wheel_path} is within the allowed size "
|
||||
f"({wheel_size_mb} MB).")
|
||||
return 0
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
if len(sys.argv) < 2:
|
||||
print("Usage: python check-wheel-size.py <directory>")
|
||||
sys.exit(1)
|
||||
|
||||
directory = sys.argv[1]
|
||||
sys.exit(check_wheel_size(directory))
|
||||
import sys
|
||||
sys.exit(check_wheel_size(sys.argv[1]))
|
||||
|
||||
@@ -1,26 +0,0 @@
|
||||
name: vllm_ci
|
||||
job_dirs:
|
||||
- ".buildkite/image_build"
|
||||
- ".buildkite/test_areas"
|
||||
- ".buildkite/hardware_tests"
|
||||
run_all_patterns:
|
||||
- "docker/Dockerfile"
|
||||
- "CMakeLists.txt"
|
||||
- "requirements/common.txt"
|
||||
- "requirements/cuda.txt"
|
||||
- "requirements/kv_connectors.txt"
|
||||
- "requirements/build/cuda.txt"
|
||||
- "requirements/test/cuda.txt"
|
||||
- "setup.py"
|
||||
- "csrc/"
|
||||
- "cmake/"
|
||||
run_all_exclude_patterns:
|
||||
- "docker/Dockerfile."
|
||||
- "csrc/cpu/"
|
||||
- "csrc/rocm/"
|
||||
- "cmake/hipify.py"
|
||||
- "cmake/cpu_extension.cmake"
|
||||
registries: public.ecr.aws/q9t5s3a7
|
||||
repositories:
|
||||
main: "vllm-ci-postmerge-repo"
|
||||
premerge: "vllm-ci-test-repo"
|
||||
@@ -1,23 +0,0 @@
|
||||
name: vllm_intel_ci
|
||||
job_dirs:
|
||||
- ".buildkite/intel_jobs"
|
||||
run_all_patterns:
|
||||
- ".buildkite/ci_config_intel.yaml"
|
||||
- ".buildkite/scripts/hardware_ci/run-intel-test.sh"
|
||||
- "docker/Dockerfile"
|
||||
- "docker/Dockerfile.xpu"
|
||||
- "CMakeLists.txt"
|
||||
- "requirements/common.txt"
|
||||
- "requirements/xpu.txt"
|
||||
- "setup.py"
|
||||
- "csrc/"
|
||||
- "cmake/"
|
||||
run_all_exclude_patterns:
|
||||
- "csrc/cpu/"
|
||||
- "csrc/rocm/"
|
||||
- "cmake/hipify.py"
|
||||
- "cmake/cpu_extension.cmake"
|
||||
registries: public.ecr.aws/q9t5s3a7
|
||||
repositories:
|
||||
main: "vllm-ci-test-repo"
|
||||
premerge: "vllm-ci-test-repo"
|
||||
@@ -1,24 +0,0 @@
|
||||
name: vllm_rocm_ci
|
||||
job_dirs:
|
||||
- ".buildkite/hardware_tests"
|
||||
run_all_patterns:
|
||||
- "docker/Dockerfile.rocm"
|
||||
- "docker/Dockerfile.rocm_base"
|
||||
- "docker/ci-rocm.hcl"
|
||||
- "docker/docker-bake-rocm.hcl"
|
||||
- ".buildkite/hardware_tests/amd.yaml"
|
||||
- ".buildkite/scripts/ci-bake-rocm.sh"
|
||||
- ".buildkite/scripts/rocm/"
|
||||
- ".buildkite/scripts/hardware_ci/run-amd-test.py"
|
||||
- ".buildkite/scripts/hardware_ci/run-amd-test.sh"
|
||||
- "CMakeLists.txt"
|
||||
- "requirements/common.txt"
|
||||
- "requirements/rocm.txt"
|
||||
- "requirements/build/rocm.txt"
|
||||
- "requirements/test/rocm.txt"
|
||||
- "setup.py"
|
||||
- "csrc/"
|
||||
- "cmake/"
|
||||
run_all_exclude_patterns:
|
||||
- "csrc/cpu/"
|
||||
- "cmake/cpu_extension.cmake"
|
||||
@@ -0,0 +1,18 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -ex
|
||||
set -o pipefail
|
||||
|
||||
(which wget && which curl) || (apt-get update && apt-get install -y wget curl)
|
||||
|
||||
# aws s3 sync s3://air-example-data-2/vllm_opensource_llava/ images/
|
||||
mkdir -p images
|
||||
cd images
|
||||
wget https://air-example-data-2.s3.us-west-2.amazonaws.com/vllm_opensource_llava/stop_sign_pixel_values.pt
|
||||
wget https://air-example-data-2.s3.us-west-2.amazonaws.com/vllm_opensource_llava/stop_sign_image_features.pt
|
||||
wget https://air-example-data-2.s3.us-west-2.amazonaws.com/vllm_opensource_llava/cherry_blossom_pixel_values.pt
|
||||
wget https://air-example-data-2.s3.us-west-2.amazonaws.com/vllm_opensource_llava/cherry_blossom_image_features.pt
|
||||
wget https://air-example-data-2.s3.us-west-2.amazonaws.com/vllm_opensource_llava/stop_sign.jpg
|
||||
wget https://air-example-data-2.s3.us-west-2.amazonaws.com/vllm_opensource_llava/cherry_blossom.jpg
|
||||
|
||||
cd -
|
||||
@@ -1,84 +0,0 @@
|
||||
group: Hardware - AMD Build
|
||||
|
||||
# ROCm image flow:
|
||||
# 1. Refresh the long-lived ROCm base image only when Dockerfile.rocm_base changes.
|
||||
# 2. Build ci_base from either the stable base or the freshly refreshed base.
|
||||
# 3. Build the per-commit ROCm CI image and smoke-test it before GPU jobs run.
|
||||
steps:
|
||||
- label: "AMD: :docker: refresh ROCm base"
|
||||
key: refresh-rocm-base-amd
|
||||
depends_on: []
|
||||
device: amd_cpu
|
||||
no_plugin: true
|
||||
commands:
|
||||
- bash .buildkite/scripts/rocm/refresh-base-image.sh
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
BUILDKIT_PROGRESS: "tty"
|
||||
TERM: "xterm-256color"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: 1 # Transient Docker/BuildKit failure
|
||||
limit: 1
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 1
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 1
|
||||
|
||||
# Ensure ci_base is up-to-date before building the test image.
|
||||
# Compares a content hash of ci_base-affecting files against the remote
|
||||
# image label. If hashes match the build is skipped (< 30 s); if they
|
||||
# differ ci_base is rebuilt and pushed automatically.
|
||||
- label: "AMD: :docker: ensure ci_base"
|
||||
key: ensure-ci-base-amd
|
||||
soft_fail: false
|
||||
depends_on:
|
||||
- refresh-rocm-base-amd
|
||||
device: amd_cpu
|
||||
no_plugin: true
|
||||
commands:
|
||||
- bash .buildkite/scripts/rocm/build-ci-base.sh
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
BUILDKIT_PROGRESS: "tty"
|
||||
TERM: "xterm-256color"
|
||||
VLLM_BAKE_FILE: "docker/docker-bake-rocm.hcl"
|
||||
PYTORCH_ROCM_ARCH: "gfx90a;gfx942;gfx950"
|
||||
REMOTE_VLLM: "1"
|
||||
VLLM_BRANCH: "$BUILDKITE_COMMIT"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: 1 # Transient Docker/BuildKit failure
|
||||
limit: 1
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 1
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 1
|
||||
|
||||
- label: "AMD: :docker: build test image and artifacts"
|
||||
key: image-build-amd
|
||||
soft_fail: false
|
||||
depends_on:
|
||||
- ensure-ci-base-amd
|
||||
device: amd_cpu
|
||||
no_plugin: true
|
||||
commands:
|
||||
- bash .buildkite/scripts/rocm/build-test-image.sh
|
||||
- bash .buildkite/scripts/rocm/smoke-test-image.sh
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
BUILDKIT_PROGRESS: "tty"
|
||||
TERM: "xterm-256color"
|
||||
VLLM_BAKE_FILE: "docker/docker-bake-rocm.hcl"
|
||||
PYTORCH_ROCM_ARCH: "gfx90a;gfx942;gfx950"
|
||||
IMAGE_TAG: "rocm/vllm-ci:$BUILDKITE_COMMIT"
|
||||
REMOTE_VLLM: "1"
|
||||
VLLM_BRANCH: "$BUILDKITE_COMMIT"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: 1 # Transient Docker/BuildKit failure
|
||||
limit: 1
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 1
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 1
|
||||
@@ -1,10 +0,0 @@
|
||||
group: Hardware
|
||||
depends_on: ~
|
||||
steps:
|
||||
- label: "Ascend NPU Test"
|
||||
soft_fail: true
|
||||
timeout_in_minutes: 20
|
||||
no_plugin: true
|
||||
device: ascend_npu
|
||||
commands:
|
||||
- bash .buildkite/scripts/hardware_ci/run-npu-test.sh
|
||||
@@ -1,170 +0,0 @@
|
||||
group: CPU
|
||||
depends_on: []
|
||||
steps:
|
||||
- label: CPU-Kernel Tests
|
||||
depends_on: []
|
||||
device: intel_cpu
|
||||
no_plugin: true
|
||||
source_file_dependencies:
|
||||
- csrc/cpu/
|
||||
- cmake/cpu_extension.cmake
|
||||
- CMakeLists.txt
|
||||
- vllm/_custom_ops.py
|
||||
- tests/kernels/attention/test_cpu_attn.py
|
||||
- tests/kernels/moe/test_cpu_fused_moe.py
|
||||
- tests/kernels/moe/test_cpu_quant_fused_moe.py
|
||||
- tests/kernels/test_onednn.py
|
||||
- tests/kernels/test_awq_int4_to_int8.py
|
||||
- tests/kernels/quantization/test_cpu_fp8_scaled_mm.py
|
||||
- tests/kernels/mamba/cpu/test_cpu_gdn_ops.py
|
||||
- tests/kernels/mamba/test_cpu_short_conv.py
|
||||
- tests/kernels/mamba/test_causal_conv1d.py
|
||||
- tests/kernels/mamba/test_mamba_ssm.py
|
||||
commands:
|
||||
- |
|
||||
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 30m "
|
||||
pytest -x -v -s tests/kernels/attention/test_cpu_attn.py
|
||||
pytest -x -v -s tests/kernels/moe/test_cpu_fused_moe.py
|
||||
pytest -x -v -s tests/kernels/moe/test_cpu_quant_fused_moe.py
|
||||
pytest -x -v -s tests/kernels/mamba/test_cpu_short_conv.py
|
||||
pytest -x -v -s tests/kernels/test_onednn.py
|
||||
pytest -x -v -s tests/kernels/test_awq_int4_to_int8.py
|
||||
pytest -x -v -s tests/kernels/quantization/test_cpu_fp8_scaled_mm.py
|
||||
pytest -x -v -s tests/kernels/mamba/cpu/test_cpu_gdn_ops.py
|
||||
pytest -x -v -s tests/kernels/mamba/test_causal_conv1d.py
|
||||
pytest -x -v -s tests/kernels/mamba/test_mamba_ssm.py"
|
||||
|
||||
# Note: SDE can't be downloaded from CI host because of AWS WAF
|
||||
# - label: CPU-Compatibility Tests
|
||||
# depends_on: []
|
||||
# device: intel_cpu
|
||||
# no_plugin: true
|
||||
# source_file_dependencies:
|
||||
# - cmake/cpu_extension.cmake
|
||||
# - setup.py
|
||||
# - vllm/platforms/cpu.py
|
||||
# commands:
|
||||
# - |
|
||||
# bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 20m "
|
||||
# bash .buildkite/scripts/hardware_ci/run-cpu-compatibility-test.sh"
|
||||
|
||||
- label: CPU-Language Generation and Pooling Model Tests
|
||||
depends_on: []
|
||||
device: intel_cpu
|
||||
no_plugin: true
|
||||
source_file_dependencies:
|
||||
- csrc/cpu/
|
||||
- vllm/
|
||||
- tests/models/language/generation/
|
||||
- tests/models/language/pooling/
|
||||
commands:
|
||||
- |
|
||||
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 50m "
|
||||
pytest -x -v -s tests/models/language/generation -m cpu_model
|
||||
pytest -x -v -s tests/models/language/pooling -m cpu_model"
|
||||
|
||||
- label: CPU-ModelRunnerV2 Tests
|
||||
depends_on: []
|
||||
device: intel_cpu
|
||||
no_plugin: true
|
||||
soft_fail: true
|
||||
source_file_dependencies:
|
||||
- vllm/v1/worker/cpu/
|
||||
- vllm/v1/worker/gpu/
|
||||
- vllm/v1/sample/ops/topk_topp_triton.py
|
||||
- vllm/v1/sample/ops/topk_topp_sampler.py
|
||||
- tests/v1/sample/test_topk_topp_sampler.py
|
||||
- tests/v1/e2e/test_cpu_linear_attn_chunked_prefix.py
|
||||
commands:
|
||||
- |
|
||||
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 45m "
|
||||
uv pip install git+https://github.com/triton-lang/triton-cpu.git@270e696d
|
||||
VLLM_USE_V2_MODEL_RUNNER=1 pytest -x -v -s tests/models/language/generation/test_granite.py -m cpu_model
|
||||
# TODO: move to CPU-Kernel Tests once triton-cpu has a pre-built wheel
|
||||
pytest -x -v -s tests/v1/sample/test_topk_topp_sampler.py::TestTritonTopkTopp
|
||||
pytest -x -v -s tests/v1/e2e/test_cpu_linear_attn_chunked_prefix.py"
|
||||
|
||||
- label: CPU-Quantization Model Tests
|
||||
depends_on: []
|
||||
device: intel_cpu
|
||||
no_plugin: true
|
||||
source_file_dependencies:
|
||||
- csrc/cpu/
|
||||
- vllm/model_executor/layers/quantization/auto_gptq.py
|
||||
- vllm/model_executor/layers/quantization/compressed_tensors/schemes/compressed_tensors_w8a8_int8.py
|
||||
- vllm/model_executor/kernels/linear/mixed_precision/cpu.py
|
||||
- vllm/model_executor/kernels/linear/scaled_mm/cpu.py
|
||||
- vllm/model_executor/layers/fused_moe/experts/cpu_moe.py
|
||||
- tests/quantization/test_compressed_tensors.py
|
||||
- tests/quantization/test_cpu_wna16.py
|
||||
- tests/quantization/test_cpu_w8a8.py
|
||||
commands:
|
||||
- |
|
||||
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 45m "
|
||||
pytest -x -v -s tests/quantization/test_compressed_tensors.py::test_compressed_tensors_w8a8_logprobs
|
||||
pytest -x -v -s tests/quantization/test_cpu_wna16.py
|
||||
pytest -x -v -s tests/quantization/test_cpu_w8a8.py"
|
||||
|
||||
- label: CPU-Distributed Tests (PP+TP)
|
||||
depends_on: []
|
||||
device: intel_cpu
|
||||
no_plugin: true
|
||||
source_file_dependencies: &cpu_distributed_deps
|
||||
- csrc/cpu/shm.cpp
|
||||
- vllm/v1/worker/cpu_worker.py
|
||||
- vllm/v1/worker/gpu_worker.py
|
||||
- vllm/v1/worker/cpu_model_runner.py
|
||||
- vllm/v1/worker/gpu_model_runner.py
|
||||
- vllm/platforms/cpu.py
|
||||
- vllm/distributed/parallel_state.py
|
||||
- vllm/distributed/device_communicators/cpu_communicator.py
|
||||
- .buildkite/scripts/hardware_ci/run-cpu-distributed-smoke-test.sh
|
||||
commands:
|
||||
- |
|
||||
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 10m "
|
||||
bash .buildkite/scripts/hardware_ci/run-cpu-distributed-smoke-test.sh tp_pp"
|
||||
|
||||
- label: CPU-Distributed Tests (DP+TP)
|
||||
depends_on: []
|
||||
device: intel_cpu
|
||||
no_plugin: true
|
||||
source_file_dependencies: *cpu_distributed_deps
|
||||
commands:
|
||||
- |
|
||||
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 10m "
|
||||
bash .buildkite/scripts/hardware_ci/run-cpu-distributed-smoke-test.sh dp_tp"
|
||||
|
||||
- label: CPU-Multi-Modal Model Tests %N
|
||||
depends_on: []
|
||||
device: intel_cpu
|
||||
no_plugin: true
|
||||
source_file_dependencies:
|
||||
# - vllm/
|
||||
- vllm/model_executor/layers/rotary_embedding
|
||||
- tests/models/multimodal/generation/
|
||||
commands:
|
||||
- |
|
||||
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 45m "
|
||||
pytest -x -v -s tests/models/multimodal/generation --ignore=tests/models/multimodal/generation/test_pixtral.py --ignore=tests/models/multimodal/generation/test_qwen2_5_vl.py -m cpu_model --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB"
|
||||
parallelism: 4
|
||||
|
||||
- label: CPU-Qwen2.5-VL Multimodal Tests
|
||||
depends_on: []
|
||||
device: intel_cpu
|
||||
no_plugin: true
|
||||
source_file_dependencies:
|
||||
# - vllm/
|
||||
- vllm/model_executor/layers/rotary_embedding
|
||||
- tests/models/multimodal/generation/
|
||||
commands:
|
||||
- |
|
||||
bash .buildkite/scripts/hardware_ci/run-cpu-test.sh 40m "
|
||||
VLLM_CI_ENV=0 pytest -x -v -s tests/models/multimodal/generation/test_qwen2_5_vl.py"
|
||||
|
||||
- label: "Arm CPU Test"
|
||||
depends_on: []
|
||||
soft_fail: false
|
||||
device: arm_cpu
|
||||
no_plugin: true
|
||||
commands:
|
||||
- bash .buildkite/scripts/hardware_ci/run-cpu-test-arm.sh
|
||||
@@ -1,10 +0,0 @@
|
||||
group: Hardware
|
||||
steps:
|
||||
- label: "GH200 Test"
|
||||
soft_fail: true
|
||||
device: gh200
|
||||
no_plugin: true
|
||||
optional: true
|
||||
commands:
|
||||
- nvidia-smi
|
||||
- bash .buildkite/scripts/hardware_ci/run-gh200-test.sh
|
||||
@@ -1,10 +0,0 @@
|
||||
group: Hardware
|
||||
depends_on: ~
|
||||
steps:
|
||||
- label: "Intel HPU Test"
|
||||
soft_fail: true
|
||||
device: intel_hpu
|
||||
no_plugin: true
|
||||
commands:
|
||||
- bash .buildkite/scripts/hardware_ci/run-hpu-test.sh
|
||||
|
||||
@@ -1,80 +0,0 @@
|
||||
group: Intel
|
||||
steps:
|
||||
- label: ":docker: Build XPU image"
|
||||
soft_fail: true
|
||||
optional: true
|
||||
depends_on: []
|
||||
key: image-build-xpu
|
||||
commands:
|
||||
- bash -lc '.buildkite/image_build/image_build_xpu.sh "public.ecr.aws/q9t5s3a7" "vllm-ci-test-repo" "$BUILDKITE_COMMIT"'
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
- label: "XPU example Test"
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
timeout_in_minutes: 50
|
||||
optional: true
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 2+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
source_file_dependencies:
|
||||
- .buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml
|
||||
- .buildkite/scripts/hardware_ci/run-intel-ci-test.sh
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh example'
|
||||
- label: "XPU V1 test"
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
timeout_in_minutes: 70
|
||||
optional: true
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
source_file_dependencies:
|
||||
- .buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml
|
||||
- .buildkite/scripts/hardware_ci/run-intel-ci-test.sh
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh v1'
|
||||
- label: "XPU server test"
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
timeout_in_minutes: 45
|
||||
optional: true
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
source_file_dependencies:
|
||||
- .buildkite/hardware_tests/intel_xpu_ci/test-intel.yaml
|
||||
- .buildkite/scripts/hardware_ci/run-intel-ci-test.sh
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'bash .buildkite/scripts/hardware_ci/run-intel-ci-test.sh server'
|
||||
@@ -1,276 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
# replace invalid characters in Docker image tags and truncate to 128 chars
|
||||
clean_docker_tag() {
|
||||
local input="$1"
|
||||
echo "$input" | sed 's/[^a-zA-Z0-9._-]/_/g' | cut -c1-128
|
||||
}
|
||||
|
||||
print_usage_and_exit() {
|
||||
echo "Usage: $0 <registry> <repo> <commit> <branch> <image_tag> [<image_tag_latest>]"
|
||||
exit 1
|
||||
}
|
||||
|
||||
print_instance_info() {
|
||||
echo ""
|
||||
echo "=== Debug: Instance Information ==="
|
||||
# Get IMDSv2 token
|
||||
if TOKEN=$(curl -s -X PUT "http://169.254.169.254/latest/api/token" \
|
||||
-H "X-aws-ec2-metadata-token-ttl-seconds: 21600" 2>/dev/null); then
|
||||
AMI_ID=$(curl -s -H "X-aws-ec2-metadata-token: $TOKEN" \
|
||||
http://169.254.169.254/latest/meta-data/ami-id 2>/dev/null || echo "unknown")
|
||||
INSTANCE_TYPE=$(curl -s -H "X-aws-ec2-metadata-token: $TOKEN" \
|
||||
http://169.254.169.254/latest/meta-data/instance-type 2>/dev/null || echo "unknown")
|
||||
INSTANCE_ID=$(curl -s -H "X-aws-ec2-metadata-token: $TOKEN" \
|
||||
http://169.254.169.254/latest/meta-data/instance-id 2>/dev/null || echo "unknown")
|
||||
AZ=$(curl -s -H "X-aws-ec2-metadata-token: $TOKEN" \
|
||||
http://169.254.169.254/latest/meta-data/placement/availability-zone 2>/dev/null || echo "unknown")
|
||||
echo "AMI ID: ${AMI_ID}"
|
||||
echo "Instance Type: ${INSTANCE_TYPE}"
|
||||
echo "Instance ID: ${INSTANCE_ID}"
|
||||
echo "AZ: ${AZ}"
|
||||
else
|
||||
echo "Not running on EC2 or IMDS not available"
|
||||
fi
|
||||
# Check for warm cache AMI (marker file baked into custom AMI)
|
||||
if [[ -f /etc/vllm-ami-info ]]; then
|
||||
echo "Cache: warm (custom vLLM AMI)"
|
||||
cat /etc/vllm-ami-info
|
||||
else
|
||||
echo "Cache: cold (standard AMI)"
|
||||
fi
|
||||
echo "==================================="
|
||||
echo ""
|
||||
}
|
||||
|
||||
setup_buildx_builder() {
|
||||
echo "--- :buildkite: Setting up buildx builder"
|
||||
if [[ -S "${BUILDKIT_SOCKET}" ]]; then
|
||||
# Custom AMI with standalone buildkitd - use remote driver for warm cache
|
||||
echo "✅ Found local buildkitd socket at ${BUILDKIT_SOCKET}"
|
||||
echo "Using remote driver to connect to buildkitd (warm cache available)"
|
||||
if docker buildx inspect baked-vllm-builder >/dev/null 2>&1; then
|
||||
echo "Using existing baked-vllm-builder"
|
||||
docker buildx use baked-vllm-builder
|
||||
else
|
||||
echo "Creating baked-vllm-builder with remote driver"
|
||||
docker buildx create \
|
||||
--name baked-vllm-builder \
|
||||
--driver remote \
|
||||
--use \
|
||||
"unix://${BUILDKIT_SOCKET}"
|
||||
fi
|
||||
docker buildx inspect --bootstrap
|
||||
elif docker buildx inspect "${BUILDER_NAME}" >/dev/null 2>&1; then
|
||||
# Existing builder available
|
||||
echo "Using existing builder: ${BUILDER_NAME}"
|
||||
docker buildx use "${BUILDER_NAME}"
|
||||
docker buildx inspect --bootstrap
|
||||
else
|
||||
# No local buildkitd, no existing builder - create new docker-container builder
|
||||
echo "No local buildkitd found, using docker-container driver"
|
||||
docker buildx create --name "${BUILDER_NAME}" --driver docker-container --use
|
||||
docker buildx inspect --bootstrap
|
||||
fi
|
||||
|
||||
# builder info
|
||||
echo "Active builder:"
|
||||
docker buildx ls | grep -E '^\*|^NAME' || docker buildx ls
|
||||
}
|
||||
|
||||
annotate_image_tags() {
|
||||
.buildkite/scripts/annotate-image-build.sh \
|
||||
"${IMAGE_TAG:-}" "${IMAGE_TAG_LATEST:-}"
|
||||
}
|
||||
|
||||
check_and_skip_if_image_exists() {
|
||||
if [[ -n "${IMAGE_TAG:-}" ]]; then
|
||||
echo "--- :mag: Checking if image exists"
|
||||
if docker manifest inspect "${IMAGE_TAG}" >/dev/null 2>&1; then
|
||||
echo "Image already exists: ${IMAGE_TAG}"
|
||||
echo "Skipping build"
|
||||
annotate_image_tags
|
||||
exit 0
|
||||
fi
|
||||
echo "Image not found, proceeding with build"
|
||||
fi
|
||||
}
|
||||
|
||||
ecr_login() {
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
|
||||
aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true
|
||||
}
|
||||
|
||||
prepare_cache_tags() {
|
||||
# resolve and set: CACHE_TO, CACHE_FROM, CACHE_FROM_BASE_BRANCH, CACHE_FROM_MAIN
|
||||
TEST_CACHE_ECR="936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-test-cache"
|
||||
MAIN_CACHE_ECR="936637512419.dkr.ecr.us-east-1.amazonaws.com/vllm-ci-postmerge-cache"
|
||||
|
||||
if [[ "$BUILDKITE_PULL_REQUEST" == "false" ]]; then
|
||||
if [[ "$BUILDKITE_BRANCH" == "main" ]]; then
|
||||
cache="${MAIN_CACHE_ECR}:latest"
|
||||
else
|
||||
clean_branch=$(clean_docker_tag "$BUILDKITE_BRANCH")
|
||||
cache="${TEST_CACHE_ECR}:${clean_branch}"
|
||||
fi
|
||||
CACHE_TO="$cache"
|
||||
CACHE_FROM="$cache"
|
||||
CACHE_FROM_BASE_BRANCH="$cache"
|
||||
else
|
||||
CACHE_TO="${TEST_CACHE_ECR}:pr-${BUILDKITE_PULL_REQUEST}"
|
||||
CACHE_FROM="${TEST_CACHE_ECR}:pr-${BUILDKITE_PULL_REQUEST}"
|
||||
if [[ "$BUILDKITE_PULL_REQUEST_BASE_BRANCH" == "main" ]]; then
|
||||
CACHE_FROM_BASE_BRANCH="${MAIN_CACHE_ECR}:latest"
|
||||
else
|
||||
clean_base=$(clean_docker_tag "$BUILDKITE_PULL_REQUEST_BASE_BRANCH")
|
||||
CACHE_FROM_BASE_BRANCH="${TEST_CACHE_ECR}:${clean_base}"
|
||||
fi
|
||||
fi
|
||||
|
||||
CACHE_FROM_MAIN="${MAIN_CACHE_ECR}:latest"
|
||||
export CACHE_TO CACHE_FROM CACHE_FROM_BASE_BRANCH CACHE_FROM_MAIN
|
||||
}
|
||||
|
||||
resolve_parent_commit() {
|
||||
if [[ -z "${PARENT_COMMIT:-}" ]]; then
|
||||
PARENT_COMMIT=$(git rev-parse HEAD~1 2>/dev/null || echo "")
|
||||
if [[ -n "${PARENT_COMMIT}" ]]; then
|
||||
echo "Computed parent commit for cache fallback: ${PARENT_COMMIT}"
|
||||
export PARENT_COMMIT
|
||||
else
|
||||
echo "Could not determine parent commit (may be first commit in repo)"
|
||||
fi
|
||||
else
|
||||
echo "Using provided PARENT_COMMIT: ${PARENT_COMMIT}"
|
||||
fi
|
||||
}
|
||||
|
||||
print_bake_config() {
|
||||
echo "--- :page_facing_up: Resolved bake configuration"
|
||||
# Write to a temp directory to avoid polluting the repo root (which is the
|
||||
# Docker build context). Files left in the repo root get COPY'd into the
|
||||
# image and can cause duplicate artifact uploads from downstream steps.
|
||||
local bake_tmp
|
||||
bake_tmp="$(mktemp -d)"
|
||||
BAKE_CONFIG_FILE="${bake_tmp}/bake-config-build-${BUILDKITE_BUILD_NUMBER:-local}.json"
|
||||
docker buildx bake -f "${VLLM_BAKE_FILE_PATH}" -f "${CI_HCL_PATH}" --print "${TARGET}" | tee "${BAKE_CONFIG_FILE}" || true
|
||||
echo "Saved bake config to ${BAKE_CONFIG_FILE}"
|
||||
echo "--- :arrow_down: Uploading bake config to Buildkite"
|
||||
(cd "$(dirname "${BAKE_CONFIG_FILE}")" && buildkite-agent artifact upload "$(basename "${BAKE_CONFIG_FILE}")")
|
||||
}
|
||||
|
||||
#################################
|
||||
# Main Script #
|
||||
#################################
|
||||
print_instance_info
|
||||
|
||||
if [[ $# -lt 5 ]]; then
|
||||
print_usage_and_exit
|
||||
fi
|
||||
|
||||
# input args
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
BRANCH=$4
|
||||
IMAGE_TAG=$5
|
||||
IMAGE_TAG_LATEST=${6:-} # only used for main branch, optional
|
||||
|
||||
# When TORCH_NIGHTLY=1, build the base CI image against PyTorch nightly so the
|
||||
# entire existing pipeline runs on nightly torch (CUDA/GPU lane only). Delegate
|
||||
# to the dedicated nightly build (PYTORCH_NIGHTLY=1, CUDA 13.0) and tag it at the
|
||||
# normal IMAGE_TAG that every test step already pulls -- no separate image tag,
|
||||
# no duplicate "vLLM Against PyTorch Nightly" pipeline section.
|
||||
if [[ "${TORCH_NIGHTLY:-0}" == "1" ]]; then
|
||||
echo "--- :warning: TORCH_NIGHTLY=1 -- building base image on PyTorch nightly"
|
||||
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||||
exec "${SCRIPT_DIR}/image_build_torch_nightly.sh" \
|
||||
"${REGISTRY}" "${REPO}" "${BUILDKITE_COMMIT}" "${BRANCH}" "${IMAGE_TAG}"
|
||||
fi
|
||||
|
||||
# build config
|
||||
TARGET="test-ci"
|
||||
VLLM_BAKE_FILE_PATH="${VLLM_BAKE_FILE_PATH:-docker/docker-bake.hcl}"
|
||||
BUILDER_NAME="${BUILDER_NAME:-vllm-builder}"
|
||||
CI_HCL_URL="${CI_HCL_URL:-https://raw.githubusercontent.com/vllm-project/ci-infra/main/docker/ci.hcl}"
|
||||
CI_HCL_PATH="/tmp/ci.hcl"
|
||||
BUILDKIT_SOCKET="/run/buildkit/buildkitd.sock"
|
||||
|
||||
prepare_cache_tags
|
||||
ecr_login
|
||||
|
||||
# Environment info (for docs and human readers)
|
||||
# VLLM_CI_BRANCH - ci-infra branch to use (default: main)
|
||||
# VLLM_BAKE_FILE_PATH - Path to vLLM's bake file (default: docker/docker-bake.hcl)
|
||||
# BUILDER_NAME - Name for buildx builder (default: vllm-builder)
|
||||
#
|
||||
# Build configuration (exported as environment variables for bake):
|
||||
export BUILDKITE_COMMIT
|
||||
export PARENT_COMMIT
|
||||
export IMAGE_TAG
|
||||
export IMAGE_TAG_LATEST
|
||||
export COMMIT="${COMMIT:-${BUILDKITE_COMMIT}}"
|
||||
export CACHE_FROM
|
||||
export CACHE_FROM_BASE_BRANCH
|
||||
export CACHE_FROM_MAIN
|
||||
export CACHE_TO
|
||||
|
||||
# print args
|
||||
echo "--- :mag: Arguments"
|
||||
echo "REGISTRY: ${REGISTRY}"
|
||||
echo "REPO: ${REPO}"
|
||||
echo "BUILDKITE_COMMIT: ${BUILDKITE_COMMIT}"
|
||||
echo "BRANCH: ${BRANCH}"
|
||||
echo "IMAGE_TAG: ${IMAGE_TAG}"
|
||||
echo "IMAGE_TAG_LATEST: ${IMAGE_TAG_LATEST}"
|
||||
|
||||
# print build configuration
|
||||
echo "--- :mag: Build configuration"
|
||||
echo "TARGET: ${TARGET}"
|
||||
echo "vLLM bake file: ${VLLM_BAKE_FILE_PATH}"
|
||||
echo "BUILDER_NAME: ${BUILDER_NAME}"
|
||||
echo "CI_HCL_URL: ${CI_HCL_URL}"
|
||||
echo "BUILDKIT_SOCKET: ${BUILDKIT_SOCKET}"
|
||||
|
||||
echo "--- :mag: Cache tags"
|
||||
echo "CACHE_TO: ${CACHE_TO}"
|
||||
echo "CACHE_FROM: ${CACHE_FROM}"
|
||||
echo "CACHE_FROM_BASE_BRANCH: ${CACHE_FROM_BASE_BRANCH}"
|
||||
echo "CACHE_FROM_MAIN: ${CACHE_FROM_MAIN}"
|
||||
|
||||
check_and_skip_if_image_exists
|
||||
|
||||
echo "--- :docker: Setting up Docker buildx bake"
|
||||
echo "Target: ${TARGET}"
|
||||
echo "vLLM bake file: ${VLLM_BAKE_FILE_PATH}"
|
||||
echo "CI HCL path: ${CI_HCL_PATH}"
|
||||
|
||||
if [[ ! -f "${VLLM_BAKE_FILE_PATH}" ]]; then
|
||||
echo "Error: vLLM bake file not found at ${VLLM_BAKE_FILE_PATH}"
|
||||
echo "Make sure you're running from the vLLM repository root"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "--- :arrow_down: Downloading ci.hcl"
|
||||
curl -sSfL -o "${CI_HCL_PATH}" "${CI_HCL_URL}"
|
||||
echo "Downloaded to ${CI_HCL_PATH}"
|
||||
|
||||
if [[ ! -f "${CI_HCL_PATH}" ]]; then
|
||||
echo "Error: ci.hcl not found at ${CI_HCL_PATH}"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
setup_buildx_builder
|
||||
|
||||
resolve_parent_commit
|
||||
export PARENT_COMMIT
|
||||
|
||||
print_bake_config
|
||||
|
||||
echo "--- :docker: Building ${TARGET}"
|
||||
docker --debug buildx bake -f "${VLLM_BAKE_FILE_PATH}" -f "${CI_HCL_PATH}" --progress plain "${TARGET}"
|
||||
|
||||
echo "--- :white_check_mark: Build complete"
|
||||
|
||||
annotate_image_tags
|
||||
@@ -1,153 +0,0 @@
|
||||
group: Abuild
|
||||
steps:
|
||||
- label: ":docker: Build image"
|
||||
key: image-build
|
||||
depends_on: []
|
||||
timeout_in_minutes: 600
|
||||
commands:
|
||||
- if [[ "$BUILDKITE_BRANCH" == "main" ]]; then .buildkite/image_build/image_build.sh $REGISTRY $REPO $BUILDKITE_COMMIT $BRANCH $IMAGE_TAG $IMAGE_TAG_LATEST; else .buildkite/image_build/image_build.sh $REGISTRY $REPO $BUILDKITE_COMMIT $BRANCH $IMAGE_TAG; fi
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
|
||||
- label: ":docker: :smoking: Non-root smoke tests"
|
||||
key: image-build-smoke-test
|
||||
depends_on:
|
||||
- image-build
|
||||
commands:
|
||||
# Smoke 1: the default (root) image must still be importable
|
||||
# under a non-root UID via `--user 2000:0`. Validates the `vllm` passwd
|
||||
# entry + group-0-writable /home/vllm + uv path cleanup from #31959.
|
||||
# Uses `import vllm` rather than `vllm serve --help` because the latter
|
||||
# instantiates `VllmConfig` which requires a GPU attached to the
|
||||
# container.
|
||||
- docker run --rm --user 2000:0 --entrypoint python3 "$IMAGE_TAG" -c "import vllm; print(vllm.__version__)"
|
||||
# Smoke 2: assert the non-root enabling invariants are baked
|
||||
# into the image. Runs as UID 2000:0 via a shell so we can verify
|
||||
# filesystem perms + passwd/group file state + wrapper presence without
|
||||
# triggering vLLM's GPU-requiring config-init path. The opt-in
|
||||
# `vllm-openai-nonroot` target adds only `USER vllm`, `WORKDIR
|
||||
# /home/vllm`, and an `ENTRYPOINT` override on top of these invariants;
|
||||
# its build correctness is reviewed at the Dockerfile level. Wrapper
|
||||
# logic is covered separately by the pre-commit hook
|
||||
# `test-nonroot-entrypoint` (see .pre-commit-config.yaml).
|
||||
- |
|
||||
docker run --rm --user 2000:0 --entrypoint /bin/sh "$IMAGE_TAG" -ec '
|
||||
if ! getent passwd 2000 | grep -q ^vllm:; then
|
||||
echo FAIL: UID 2000 != vllm
|
||||
exit 1
|
||||
fi
|
||||
if ! id -gn 2>/dev/null | grep -qx root; then
|
||||
echo FAIL: GID 0 not root group
|
||||
exit 1
|
||||
fi
|
||||
touch /home/vllm/.smoke && rm /home/vllm/.smoke
|
||||
touch /opt/uv/cache/.smoke && rm /opt/uv/cache/.smoke
|
||||
if ! test -x /usr/local/bin/vllm-nonroot-entrypoint.sh; then
|
||||
echo FAIL: wrapper missing
|
||||
exit 1
|
||||
fi
|
||||
if ! test -w /etc/passwd; then
|
||||
echo FAIL: /etc/passwd not group-writable
|
||||
exit 1
|
||||
fi
|
||||
if ! test -w /etc/group; then
|
||||
echo FAIL: /etc/group not group-writable
|
||||
exit 1
|
||||
fi
|
||||
echo non-root invariants OK
|
||||
'
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
|
||||
- label: ":docker: Build CPU image"
|
||||
key: image-build-cpu
|
||||
depends_on: []
|
||||
commands:
|
||||
- .buildkite/image_build/image_build_cpu.sh $REGISTRY $REPO $BUILDKITE_COMMIT
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
|
||||
- label: ":docker: Build Zen CPU image"
|
||||
key: image-build-zen-cpu
|
||||
# Minimal confirmation build: run the zen image build on the generic x86
|
||||
# premerge queue to verify it succeeds. Reuses the shared `-cpu` image as its
|
||||
# base, so it must run after the CPU image build.
|
||||
#
|
||||
# No source_file_dependencies: this step always runs for this validation PR
|
||||
# so the build is exercised regardless of which files changed.
|
||||
depends_on:
|
||||
- image-build-cpu
|
||||
agents:
|
||||
queue: small_cpu_queue_premerge
|
||||
commands:
|
||||
- .buildkite/image_build/image_build_zen_cpu.sh $REGISTRY $REPO $BUILDKITE_COMMIT
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
|
||||
- label: ":docker: Build HPU image"
|
||||
soft_fail: true
|
||||
depends_on: []
|
||||
key: image-build-hpu
|
||||
commands:
|
||||
- .buildkite/image_build/image_build_hpu.sh $REGISTRY $REPO $BUILDKITE_COMMIT
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
|
||||
- label: ":docker: Build CPU arm64 image"
|
||||
key: cpu-arm64-image-build
|
||||
depends_on: []
|
||||
optional: true
|
||||
commands:
|
||||
- .buildkite/image_build/image_build_cpu_arm64.sh $REGISTRY $REPO $BUILDKITE_COMMIT
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
|
||||
- label: ":docker: Build arm64 image"
|
||||
key: arm64-image-build
|
||||
depends_on: []
|
||||
source_file_dependencies:
|
||||
- ".buildkite/image_build/image_build.yaml"
|
||||
- ".buildkite/image_build/image_build_arm64.sh"
|
||||
- "docker/Dockerfile"
|
||||
commands:
|
||||
- .buildkite/image_build/image_build_arm64.sh $REGISTRY $REPO $BUILDKITE_COMMIT
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
@@ -1,39 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
if [[ $# -lt 3 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-arm64"
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
|
||||
|
||||
# skip build if image already exists
|
||||
if docker manifest inspect "$IMAGE" >/dev/null 2>&1; then
|
||||
echo "Image found"
|
||||
else
|
||||
echo "Image not found, proceeding with build..."
|
||||
# build for arm64 GPU targets: Grace/GH200 (sm_90),
|
||||
# Blackwell/Thor (sm_100/sm_103/sm_110), and DGX Spark/GB10
|
||||
# (sm_121, family-covered by 12.0 under CUDA 13)
|
||||
docker build --file docker/Dockerfile \
|
||||
--platform linux/arm64 \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg nvcc_threads=4 \
|
||||
--build-arg torch_cuda_arch_list="9.0 10.0 11.0 12.0" \
|
||||
--build-arg USE_SCCACHE=1 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--tag "$IMAGE" \
|
||||
--target test \
|
||||
--progress plain .
|
||||
# push
|
||||
docker push "$IMAGE"
|
||||
fi
|
||||
|
||||
.buildkite/scripts/annotate-image-build.sh "$IMAGE"
|
||||
@@ -1,34 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
if [[ $# -lt 3 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-cpu"
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
|
||||
|
||||
# skip build if image already exists
|
||||
if docker manifest inspect "$IMAGE" >/dev/null 2>&1; then
|
||||
echo "Image found"
|
||||
else
|
||||
echo "Image not found, proceeding with build..."
|
||||
# build
|
||||
docker build --file docker/Dockerfile.cpu \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--build-arg VLLM_CPU_X86=true \
|
||||
--tag "$IMAGE" \
|
||||
--target vllm-test \
|
||||
--progress plain .
|
||||
# push
|
||||
docker push "$IMAGE"
|
||||
fi
|
||||
|
||||
.buildkite/scripts/annotate-image-build.sh "$IMAGE"
|
||||
@@ -1,33 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
if [[ $# -lt 3 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-arm64-cpu"
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
|
||||
|
||||
# skip build if image already exists
|
||||
if docker manifest inspect "$IMAGE" >/dev/null 2>&1; then
|
||||
echo "Image found"
|
||||
else
|
||||
echo "Image not found, proceeding with build..."
|
||||
# build
|
||||
docker build --file docker/Dockerfile.cpu \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--tag "$IMAGE" \
|
||||
--target vllm-test \
|
||||
--progress plain .
|
||||
# push
|
||||
docker push "$IMAGE"
|
||||
fi
|
||||
|
||||
.buildkite/scripts/annotate-image-build.sh "$IMAGE"
|
||||
@@ -1,34 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
if [[ $# -lt 3 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-hpu"
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
|
||||
|
||||
# skip build if image already exists
|
||||
if docker manifest inspect "$IMAGE" >/dev/null 2>&1; then
|
||||
echo "Image found"
|
||||
else
|
||||
echo "Image not found, proceeding with build..."
|
||||
# build
|
||||
docker build \
|
||||
--file tests/pytorch_ci_hud_benchmark/Dockerfile.hpu \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--tag "$IMAGE" \
|
||||
--progress plain \
|
||||
https://github.com/vllm-project/vllm-gaudi.git
|
||||
# push
|
||||
docker push "$IMAGE"
|
||||
fi
|
||||
|
||||
.buildkite/scripts/annotate-image-build.sh "$IMAGE"
|
||||
@@ -1,71 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -euo pipefail
|
||||
|
||||
# Build a vLLM test image with PyTorch nightly installed.
|
||||
# Called by the pipeline generator's "vLLM Against PyTorch Nightly" group.
|
||||
|
||||
if [[ $# -lt 5 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit> <branch> <image_tag>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
BRANCH=$4
|
||||
IMAGE_TAG=$5
|
||||
|
||||
# --- Arguments ---
|
||||
echo "--- :mag: Arguments"
|
||||
echo "REGISTRY: ${REGISTRY}"
|
||||
echo "REPO: ${REPO}"
|
||||
echo "BUILDKITE_COMMIT: ${BUILDKITE_COMMIT}"
|
||||
echo "BRANCH: ${BRANCH}"
|
||||
echo "IMAGE_TAG: ${IMAGE_TAG}"
|
||||
|
||||
# --- ECR login ---
|
||||
echo "--- :key: ECR login"
|
||||
aws ecr-public get-login-password --region us-east-1 \
|
||||
| docker login --username AWS --password-stdin "$REGISTRY"
|
||||
aws ecr get-login-password --region us-east-1 \
|
||||
| docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com
|
||||
|
||||
# --- Set up buildx ---
|
||||
echo "--- :docker: Setting up buildx"
|
||||
docker buildx create --name vllm-builder --driver docker-container --use || true
|
||||
docker buildx inspect --bootstrap
|
||||
docker buildx ls
|
||||
|
||||
# --- Skip if image already exists ---
|
||||
echo "--- :mag: Checking if image already exists"
|
||||
if docker manifest inspect "$IMAGE_TAG" >/dev/null 2>&1; then
|
||||
echo "Image found: $IMAGE_TAG — skipping build"
|
||||
.buildkite/scripts/annotate-image-build.sh "$IMAGE_TAG"
|
||||
exit 0
|
||||
fi
|
||||
echo "Image not found, proceeding with build..."
|
||||
|
||||
# --- CUDA 13.0 for nightly builds ---
|
||||
# Nightly CI uses CUDA 13.0 while regular CI stays on CUDA 12.9
|
||||
NIGHTLY_CUDA_VERSION="13.0.2"
|
||||
NIGHTLY_BUILD_BASE_IMAGE="nvidia/cuda:${NIGHTLY_CUDA_VERSION}-devel-ubuntu22.04"
|
||||
NIGHTLY_FINAL_BASE_IMAGE="nvidia/cuda:${NIGHTLY_CUDA_VERSION}-base-ubuntu22.04"
|
||||
|
||||
echo "--- :docker: Building torch nightly image (CUDA ${NIGHTLY_CUDA_VERSION})"
|
||||
docker buildx build --file docker/Dockerfile \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--build-arg USE_SCCACHE=1 \
|
||||
--build-arg PYTORCH_NIGHTLY=1 \
|
||||
--build-arg CUDA_VERSION="${NIGHTLY_CUDA_VERSION}" \
|
||||
--build-arg BUILD_BASE_IMAGE="${NIGHTLY_BUILD_BASE_IMAGE}" \
|
||||
--build-arg FINAL_BASE_IMAGE="${NIGHTLY_FINAL_BASE_IMAGE}" \
|
||||
--build-arg torch_cuda_arch_list="8.0 8.9 9.0 10.0 12.0" \
|
||||
--tag "$IMAGE_TAG" \
|
||||
--push \
|
||||
--target test \
|
||||
--progress plain .
|
||||
|
||||
echo "--- :white_check_mark: Torch nightly image build complete: $IMAGE_TAG"
|
||||
|
||||
.buildkite/scripts/annotate-image-build.sh "$IMAGE_TAG"
|
||||
@@ -1,34 +0,0 @@
|
||||
#!/bin/bash
|
||||
set -e
|
||||
|
||||
if [[ $# -lt 3 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-xpu"
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
|
||||
aws ecr get-login-password --region us-east-1 | docker login --username AWS --password-stdin 936637512419.dkr.ecr.us-east-1.amazonaws.com || true
|
||||
|
||||
# skip build if image already exists
|
||||
if docker manifest inspect "$IMAGE" &> /dev/null; then
|
||||
echo "Image found"
|
||||
else
|
||||
echo "Image not found, proceeding with build..."
|
||||
# build
|
||||
docker build \
|
||||
--file docker/Dockerfile.xpu \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--tag "$IMAGE" \
|
||||
--progress plain .
|
||||
# push
|
||||
docker push "$IMAGE"
|
||||
fi
|
||||
|
||||
.buildkite/scripts/annotate-image-build.sh "$IMAGE"
|
||||
@@ -1,51 +0,0 @@
|
||||
#!/bin/bash
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
#
|
||||
# Build the AMD Zen CPU image (vLLM + zentorch) as a two-step layered build:
|
||||
# 1. a CPU base image (vLLM installed) built from docker/Dockerfile.cpu
|
||||
# 2. docker/Dockerfile.zen --target vllm-zen-test -> zen image on top
|
||||
#
|
||||
# The image is (re)built from source every time, mirroring
|
||||
# .buildkite/scripts/hardware_ci/run-cpu-test.sh. It is not pushed to a registry.
|
||||
#
|
||||
# See docker/Dockerfile.zen for the build workflow this mirrors.
|
||||
set -e
|
||||
|
||||
if [[ $# -lt 3 ]]; then
|
||||
echo "Usage: $0 <registry> <repo> <commit>"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
REGISTRY=$1
|
||||
REPO=$2
|
||||
BUILDKITE_COMMIT=$3
|
||||
|
||||
# Local image tags (not pushed).
|
||||
BASE_IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-cpu-base-for-zen"
|
||||
IMAGE="$REGISTRY/$REPO:$BUILDKITE_COMMIT-zen-cpu"
|
||||
|
||||
# ZENTORCH_VERSION is optional; when unset the Dockerfile falls back to
|
||||
# installing zentorch via `vllm[zen]`.
|
||||
ZENTORCH_VERSION=${ZENTORCH_VERSION:-}
|
||||
|
||||
# Step 1: build the CPU base image that Dockerfile.zen layers on.
|
||||
echo "--- :docker: Building CPU base image"
|
||||
docker build --file docker/Dockerfile.cpu \
|
||||
--platform linux/amd64 \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--build-arg VLLM_CPU_X86=true \
|
||||
--tag "$BASE_IMAGE" \
|
||||
--target vllm-openai \
|
||||
--progress plain .
|
||||
|
||||
# Step 2: build the zen test image on top of the CPU base.
|
||||
echo "--- :docker: Building Zen test image"
|
||||
docker build --file docker/Dockerfile.zen \
|
||||
--platform linux/amd64 \
|
||||
--build-arg BASE_IMAGE="$BASE_IMAGE" \
|
||||
${ZENTORCH_VERSION:+--build-arg ZENTORCH_VERSION="$ZENTORCH_VERSION"} \
|
||||
--tag "$IMAGE" \
|
||||
--target vllm-zen-test \
|
||||
--progress plain .
|
||||
@@ -1,27 +0,0 @@
|
||||
group: Basic Correctness
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: XPU Sleep Mode
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/basic_correctness/test_cumem.py
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
pytest -v -s basic_correctness/test_cpu_offload.py &&
|
||||
pytest -v -s basic_correctness/test_mem.py::test_end_to_end'
|
||||
@@ -1,25 +0,0 @@
|
||||
group: Engine Intel
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: Engine (1 GPU)
|
||||
timeout_in_minutes: 30
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/v1/engine/
|
||||
- tests/v1/engine/
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py'
|
||||
@@ -1,27 +0,0 @@
|
||||
group: Expert Parallelism
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: EPLB Algorithm
|
||||
key: eplb-algorithm
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/distributed/eplb
|
||||
- tests/distributed/test_eplb_algo.py
|
||||
- tests/distributed/test_eplb_utils.py
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s distributed/test_eplb_algo.py'
|
||||
@@ -1,25 +0,0 @@
|
||||
group: Kernels Intel
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: vLLM IR Tests
|
||||
timeout_in_minutes: 30
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/ir
|
||||
- vllm/kernels
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s kernels/ir'
|
||||
@@ -1,161 +0,0 @@
|
||||
group: LoRA Intel
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: LoRA Runtime + Utils
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/lora
|
||||
- tests/lora
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
pytest -v -s lora/test_layers.py &&
|
||||
pytest -v -s lora/test_lora_checkpoints.py &&
|
||||
pytest -v -s lora/test_lora_functions.py &&
|
||||
pytest -v -s lora/test_lora_huggingface.py &&
|
||||
pytest -v -s lora/test_lora_manager.py &&
|
||||
pytest -v -s lora/test_lora_utils.py &&
|
||||
pytest -v -s lora/test_peft_helper.py &&
|
||||
pytest -v -s lora/test_resolver.py &&
|
||||
pytest -v -s lora/test_utils.py &&
|
||||
pytest -v -s lora/test_add_lora.py &&
|
||||
pytest -v -s lora/test_worker.py'
|
||||
|
||||
- label: LoRA Fused/MoE Kernels
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/lora
|
||||
- tests/lora
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
pytest -v -s lora/test_fused_moe_lora_kernel.py &&
|
||||
pytest -v -s lora/test_moe_lora_align_sum.py --deselect="tests/lora/test_moe_lora_align_sum.py::test_moe_lora_align_block_size_mixed_base_and_lora[1]"'
|
||||
|
||||
- label: LoRA Punica Kernels
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/lora
|
||||
- tests/lora
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
set -o pipefail &&
|
||||
pytest -v -s lora/test_punica_ops.py::test_kernels &&
|
||||
pytest -v -s lora/test_punica_ops.py::test_kernels_hidden_size &&
|
||||
pytest -v -s lora/test_punica_ops.py::test_add_lora_fused_moe_early_exit'
|
||||
|
||||
- label: LoRA Punica FP8/XPU Ops
|
||||
timeout_in_minutes: 60
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/lora
|
||||
- tests/lora
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
pytest -v -s lora/test_punica_ops_fp8.py &&
|
||||
pytest -v -s lora/test_punica_xpu_ops.py'
|
||||
|
||||
- label: LoRA Models
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 2+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/lora
|
||||
- tests/lora
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
pytest -v -s lora/test_quant_model.py --deselect="tests/lora/test_quant_model.py::test_quant_model_lora[model0]" --deselect="tests/lora/test_quant_model.py::test_quant_model_lora[model1]" --deselect="tests/lora/test_quant_model.py::test_quant_model_tp_equality[model0]" &&
|
||||
pytest -v -s lora/test_transformers_model.py &&
|
||||
pytest -v -s lora/test_chatglm3_tp.py &&
|
||||
pytest -v -s lora/test_llama_tp.py::test_llama_lora &&
|
||||
pytest -s -v lora/test_minicpmv_tp.py'
|
||||
|
||||
- label: LoRA Multimodal
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/lora
|
||||
- tests/lora
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
pytest -v -s lora/test_default_mm_loras.py &&
|
||||
pytest -v -s lora/test_whisper.py'
|
||||
@@ -1,261 +0,0 @@
|
||||
group: Miscellaneous Intel
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: V1 Core + KV + Metrics
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/v1/core
|
||||
- tests/v1/executor
|
||||
- tests/v1/kv_offload
|
||||
- tests/v1/worker
|
||||
- tests/v1/kv_connector/unit
|
||||
- tests/v1/metrics
|
||||
- tests/entrypoints/openai/correctness/test_lmeval.py
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'pip install -r requirements/kv_connectors.txt &&
|
||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
cd tests &&
|
||||
pytest -v -s v1/executor'
|
||||
|
||||
- label: V1 Sample + Logits
|
||||
timeout_in_minutes: 90
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/config/
|
||||
- vllm/distributed/
|
||||
- vllm/engine/
|
||||
- vllm/inputs/
|
||||
- vllm/logger.py
|
||||
- vllm/model_executor/
|
||||
- vllm/platforms/
|
||||
- vllm/sampling_params.py
|
||||
- vllm/transformers_utils/
|
||||
- vllm/utils/
|
||||
- vllm/v1/
|
||||
- tests/v1/sample
|
||||
- tests/v1/logits_processors
|
||||
- tests/v1/test_oracle.py
|
||||
- tests/v1/test_request.py
|
||||
- tests/v1/test_outputs.py
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'pip install lm_eval[api]>=0.4.12 &&
|
||||
export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
cd tests &&
|
||||
pytest -v -s v1/logits_processors --ignore=v1/logits_processors/test_custom_online.py --ignore=v1/logits_processors/test_custom_offline.py &&
|
||||
pytest -v -s v1/test_oracle.py &&
|
||||
pytest -v -s v1/test_request.py &&
|
||||
pytest -v -s v1/test_outputs.py &&
|
||||
pytest -v -s v1/sample'
|
||||
|
||||
- label: Basic Models Tests (Initialization)
|
||||
timeout_in_minutes: 60
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/models/test_initialization.py
|
||||
- tests/models/registry.py
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'export VLLM_XPU_FUSED_MOE_USE_REF=1 &&
|
||||
cd tests &&
|
||||
pytest -v -s models/test_initialization.py::test_can_initialize_large_subset[Eagle3MiniMaxM2ForCausalLM]'
|
||||
|
||||
- label: XPU CPU Offload
|
||||
timeout_in_minutes: 60
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- vllm/v1/kv_offload/
|
||||
- vllm/v1/kv_connector/
|
||||
- tests/v1/kv_offload/
|
||||
- tests/v1/kv_connector/unit/test_offloading_connector.py
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'export VLLM_WORKER_MULTIPROC_METHOD=spawn &&
|
||||
cd tests &&
|
||||
pytest -v -s v1/kv_offload &&
|
||||
pytest -v -s v1/kv_connector/unit/test_offloading_connector.py'
|
||||
|
||||
- label: NixlConnector PD accuracy (2 GPUs)
|
||||
timeout_in_minutes: 60
|
||||
num_devices: 2
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 2+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/distributed/kv_transfer/kv_connector/v1/nixl/
|
||||
- vllm/v1/worker/kv_connector_model_runner_mixin.py
|
||||
- tests/v1/kv_connector/nixl_integration/
|
||||
- vllm/platforms/xpu.py
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
bash v1/kv_connector/nixl_integration/run_xpu_disagg_accuracy_test.sh'
|
||||
|
||||
- label: Regression
|
||||
key: regression
|
||||
timeout_in_minutes: 50
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/config/
|
||||
- vllm/distributed/
|
||||
- vllm/engine/
|
||||
- vllm/inputs/
|
||||
- vllm/model_executor/
|
||||
- vllm/multimodal/
|
||||
- vllm/platforms/
|
||||
- vllm/sampling_params.py
|
||||
- vllm/transformers_utils/
|
||||
- vllm/utils/
|
||||
- vllm/v1/
|
||||
- tests/test_regression
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'pip install modelscope\<1.38 &&
|
||||
cd tests &&
|
||||
pytest -v -s test_regression.py'
|
||||
|
||||
- label: Metrics, Tracing (2 GPUs)
|
||||
key: metrics-tracing-2-gpus
|
||||
timeout_in_minutes: 45
|
||||
num_devices: 2
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 2+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/config/
|
||||
- vllm/distributed/
|
||||
- vllm/engine/
|
||||
- vllm/inputs/
|
||||
- vllm/model_executor/
|
||||
- vllm/multimodal/
|
||||
- vllm/platforms/
|
||||
- vllm/sampling_params.py
|
||||
- vllm/tracing/
|
||||
- vllm/transformers_utils/
|
||||
- vllm/utils/
|
||||
- vllm/v1/
|
||||
- tests/v1/tracing
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'pip install opentelemetry-sdk\>=1.26.0 opentelemetry-api\>=1.26.0 opentelemetry-exporter-otlp\>=1.26.0 opentelemetry-semantic-conventions-ai\>=0.4.1 &&
|
||||
cd tests &&
|
||||
pytest -v -s v1/tracing'
|
||||
|
||||
- label: Async Engine, Inputs, Utils, Worker
|
||||
key: async-engine-inputs-utils-worker
|
||||
timeout_in_minutes: 55
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/assets/
|
||||
- vllm/config/
|
||||
- vllm/distributed/
|
||||
- vllm/engine/
|
||||
- vllm/inputs/
|
||||
- vllm/model_executor/
|
||||
- vllm/multimodal/
|
||||
- vllm/platforms/
|
||||
- vllm/sampling_params.py
|
||||
- vllm/tokenizers/
|
||||
- vllm/transformers_utils/
|
||||
- vllm/utils/
|
||||
- vllm/v1/
|
||||
- tests/detokenizer
|
||||
- tests/multimodal
|
||||
- tests/utils_
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pip install av &&
|
||||
pytest -v -s detokenizer &&
|
||||
pytest -v -s -m "not cpu_test" ./multimodal &&
|
||||
pytest -v -s utils_ --ignore=utils_/test_mem_utils.py'
|
||||
@@ -1,62 +0,0 @@
|
||||
group: Model Runner V2 Intel
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: Model Runner V2 Core Tests (Intel)
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 2+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/v1/worker/gpu/
|
||||
- vllm/v1/worker/gpu_worker.py
|
||||
- vllm/v1/core/sched/
|
||||
- vllm/v1/attention/
|
||||
- tests/v1/engine/test_llm_engine.py
|
||||
- tests/v1/e2e/
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'export VLLM_USE_V2_MODEL_RUNNER=1 &&
|
||||
cd tests &&
|
||||
pytest -v -s v1/engine/test_llm_engine.py -k "not test_engine_metrics" &&
|
||||
ENFORCE_EAGER=1 pytest -v -s v1/e2e/general/test_async_scheduling.py -k "not ngram" &&
|
||||
pytest -v -s v1/e2e/general/test_min_tokens.py'
|
||||
|
||||
- label: Model Runner V2 Examples (Intel)
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/v1/worker/gpu/
|
||||
- vllm/v1/core/sched/
|
||||
- vllm/v1/worker/gpu_worker.py
|
||||
- examples/basic/offline_inference/
|
||||
- examples/generate/multimodal/
|
||||
- examples/features/
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'export VLLM_USE_V2_MODEL_RUNNER=1 &&
|
||||
cd examples &&
|
||||
python3 basic/offline_inference/chat.py &&
|
||||
python3 basic/offline_inference/generate.py --model facebook/opt-125m &&
|
||||
python3 generate/multimodal/vision_language_offline.py --seed 0 &&
|
||||
python3 features/automatic_prefix_caching/prefix_caching_offline.py'
|
||||
@@ -1,27 +0,0 @@
|
||||
group: Models - Distributed
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: Distributed Model Tests (2 GPUs)
|
||||
key: distributed-model-tests-2-gpus
|
||||
timeout_in_minutes: 65
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 2+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/model_executor/model_loader/sharded_state_loader.py
|
||||
- vllm/model_executor/models/
|
||||
- tests/model_executor/model_loader/test_sharded_state_loader.py
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s model_executor/model_loader/test_sharded_state_loader.py -m "not slow_test"'
|
||||
@@ -1,127 +0,0 @@
|
||||
group: Models - Multimodal
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: "Multi-Modal Models (Standard) 1: qwen2"
|
||||
key: multi-modal-models-standard-1-qwen2
|
||||
timeout_in_minutes: 70
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/models/multimodal
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'pip install av &&
|
||||
cd tests &&
|
||||
pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "qwen2" &&
|
||||
pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model'
|
||||
|
||||
- label: "Multi-Modal Models (Standard) 2: qwen3 + gemma"
|
||||
key: multi-modal-models-standard-2-qwen3-gemma
|
||||
timeout_in_minutes: 70
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/models/multimodal
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s models/multimodal/generation/test_qwen2_5_vl.py -m core_model'
|
||||
|
||||
- label: "Multi-Modal Models (Standard) 3: llava + qwen2_vl"
|
||||
key: multi-modal-models-standard-3-llava-qwen2-vl
|
||||
timeout_in_minutes: 65
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/models/multimodal
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s models/multimodal/generation/test_common.py -m core_model -k "not qwen2 and not qwen3 and not gemma" &&
|
||||
pytest -v -s models/multimodal/generation/test_qwen2_vl.py -m core_model'
|
||||
|
||||
- label: "Multi-Modal Models (Standard) 4: other + whisper"
|
||||
key: multi-modal-models-standard-4-other-whisper
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/models/multimodal
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'pip install av &&
|
||||
cd tests &&
|
||||
pytest -v -s models/multimodal -m core_model --ignore models/multimodal/generation/test_common.py --ignore models/multimodal/generation/test_ultravox.py --ignore models/multimodal/generation/test_qwen2_5_vl.py --ignore models/multimodal/generation/test_qwen2_vl.py --ignore models/multimodal/generation/test_whisper.py --ignore models/multimodal/generation/test_memory_leak.py --ignore models/multimodal/processing'
|
||||
|
||||
- label: Multi-Modal Processor # 44min
|
||||
key: multi-modal-processor
|
||||
timeout_in_minutes: 60
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/models/multimodal
|
||||
- tests/models/registry.py
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'pip install av matplotlib ftfy &&
|
||||
pip install open-clip-torch --no-deps &&
|
||||
cd tests &&
|
||||
pytest -v -s models/multimodal/processing/test_tensor_schema.py
|
||||
--num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB'
|
||||
parallelism: 4
|
||||
@@ -1,28 +0,0 @@
|
||||
group: Quantization
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: Quantization
|
||||
key: quantization
|
||||
timeout_in_minutes: 30
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
no_plugin: true
|
||||
working_dir: "."
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
source_file_dependencies:
|
||||
- csrc/
|
||||
- vllm/model_executor/layers/quantization
|
||||
- tests/quantization
|
||||
commands:
|
||||
# - VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s quantization/ --ignore quantization/test_blackwell_moe.py
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'VLLM_TEST_FORCE_LOAD_FORMAT=auto pytest -v -s tests/quantization/test_per_token_kv_cache.py --deselect="tests/quantization/test_per_token_kv_cache.py::test_triton_unified_attention_per_token_head_scale[int4-16-128-num_heads0-seq_lens1]"'
|
||||
|
||||
@@ -1,171 +0,0 @@
|
||||
group: Intel
|
||||
steps:
|
||||
- label: ":docker: Build XPU image"
|
||||
soft_fail: true
|
||||
depends_on: []
|
||||
key: image-build-xpu
|
||||
commands:
|
||||
- bash -lc '.buildkite/image_build/image_build_xpu.sh "public.ecr.aws/q9t5s3a7" "vllm-ci-test-repo" "$BUILDKITE_COMMIT"'
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 2
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 2
|
||||
- label: "XPU example Test"
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
timeout_in_minutes: 50
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 2+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- .buildkite/intel_jobs/test-intel.yaml
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'pip install tblib==3.1.0 &&
|
||||
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager &&
|
||||
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 -O3 -cc.cudagraph_mode=NONE &&
|
||||
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager -tp 2 --distributed-executor-backend mp &&
|
||||
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --attention-backend=TRITON_ATTN &&
|
||||
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --quantization fp8 &&
|
||||
python3 examples/basic/offline_inference/generate.py --model facebook/opt-125m --block-size 64 --enforce-eager --kv-cache-dtype fp8 &&
|
||||
python3 examples/basic/offline_inference/generate.py --model nvidia/Llama-3.1-8B-Instruct-FP8 --block-size 64 --enforce-eager --quantization modelopt --kv-cache-dtype fp8 --attention-backend TRITON_ATTN --max-model-len 4096 &&
|
||||
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --block-size 64 --enforce-eager --max-model-len 8192 &&
|
||||
python3 examples/basic/offline_inference/generate.py --model TheBloke/TinyLlama-1.1B-Chat-v0.3-AWQ --block-size 64 --enforce-eager &&
|
||||
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 &&
|
||||
python3 examples/basic/offline_inference/generate.py --model ibm-research/PowerMoE-3b --block-size 64 --enforce-eager -tp 2 --enable-expert-parallel &&
|
||||
python3 examples/basic/offline_inference/generate.py --model superjob/Qwen3-4B-Instruct-2507-GPTQ-Int4 --max-model-len 8192 &&
|
||||
VLLM_XPU_FUSED_MOE_USE_REF=1 python3 examples/basic/offline_inference/generate.py --model Qwen/Qwen3-30B-A3B-Instruct-2507-FP8 --enforce-eager -tp 2 --max-model-len 8192 &&
|
||||
python3 examples/basic/offline_inference/generate.py --model INCModel/Qwen3-30B-A3B-Instruct-2507-MXFP4-LLMC --enforce-eager -tp 2 --max-model-len 8192
|
||||
'
|
||||
- label: "XPU W8A8 FP8 Linear Examples"
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
timeout_in_minutes: 60
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- .buildkite/intel_jobs/test-intel.yaml
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model RedHatAI/Meta-Llama-3.1-8B-Instruct-FP8 --enforce-eager --max-model-len 4096 &&
|
||||
python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model neuralmagic/Llama-3.2-1B-Instruct-FP8-dynamic --enforce-eager --max-model-len 4096 &&
|
||||
python3 examples/basic/offline_inference/generate.py --linear-backend xpu --model meta-llama/Llama-3.2-1B-Instruct --quantization fp8 --enforce-eager --max-model-len 4096
|
||||
'
|
||||
- label: "XPU V1 test"
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
timeout_in_minutes: 70
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 24+
|
||||
no_plugin: true
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- .buildkite/intel_jobs/test-intel.yaml
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s v1/core --ignore=v1/core/test_reset_prefix_cache_e2e.py --ignore=v1/core/test_scheduler_e2e.py &&
|
||||
pytest -v -s v1/engine --ignore=v1/engine/test_output_processor.py &&
|
||||
pytest -v -s v1/sample --ignore=v1/sample/test_logprobs.py --ignore=v1/sample/test_logprobs_e2e.py -k "not test_topk_only and not test_topp_only and not test_topk_and_topp" &&
|
||||
pytest -v -s v1/worker --ignore=v1/worker/test_gpu_model_runner.py --ignore=v1/worker/test_worker_memory_snapshot.py &&
|
||||
pytest -v -s v1/structured_output &&
|
||||
pytest -v -s v1/test_serial_utils.py &&
|
||||
pytest -v -s v1/e2e/general/test_correctness_sliding_window.py --deselect="tests/v1/e2e/general/test_correctness_sliding_window.py::test_sliding_window_retrieval[True-1-5-google/gemma-3-1b-it]" &&
|
||||
pytest -v -s v1/spec_decode --ignore=v1/spec_decode/test_max_len.py --ignore=v1/spec_decode/test_speculators_eagle3.py --ignore=v1/spec_decode/test_acceptance_length.py --ignore=v1/spec_decode/test_speculators_correctness.py &&
|
||||
pytest -v -s v1/kv_connector/unit --ignore=v1/kv_connector/unit/test_multi_connector.py --ignore=v1/kv_connector/unit/test_example_connector.py --ignore=v1/kv_connector/unit/test_lmcache_integration.py --ignore=v1/kv_connector/unit/test_hf3fs_client.py --ignore=v1/kv_connector/unit/test_hf3fs_connector.py --ignore=v1/kv_connector/unit/test_hf3fs_metadata_server.py --ignore=v1/kv_connector/unit/test_offloading_connector.py'
|
||||
- label: "XPU server test"
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
timeout_in_minutes: 45
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- .buildkite/intel_jobs/test-intel.yaml
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'pip install av &&
|
||||
cd tests &&
|
||||
pytest -v -s entrypoints/multimodal/openai/chat_completion/test_audio_in_video.py &&
|
||||
pytest -v -s benchmarks/test_serve_cli.py'
|
||||
- label: "XPU quantization test"
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
timeout_in_minutes: 30
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- .buildkite/intel_jobs/test-intel.yaml
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s quantization/test_auto_round.py'
|
||||
- label: "XPU compressed tensors FP8 test"
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
timeout_in_minutes: 60
|
||||
device: intel_gpu
|
||||
agent_tags:
|
||||
label: production
|
||||
gpu: 1+
|
||||
mem: 16+
|
||||
no_plugin: true
|
||||
env:
|
||||
REGISTRY: "public.ecr.aws/q9t5s3a7"
|
||||
REPO: "vllm-ci-test-repo"
|
||||
VLLM_TEST_DEVICE: "xpu"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/quantization/test_compressed_tensors.py
|
||||
- .buildkite/intel_jobs/test-intel.yaml
|
||||
commands:
|
||||
- >-
|
||||
bash .buildkite/scripts/hardware_ci/run-intel-test.sh
|
||||
'cd tests &&
|
||||
pytest -v -s quantization/test_compressed_tensors.py::test_compressed_tensors_fp8'
|
||||
@@ -1,13 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m deepseek-ai/DeepSeek-V2-Lite-Chat -b "auto" -l 1000 -f 5 -t 2
|
||||
model_name: "deepseek-ai/DeepSeek-V2-Lite-Chat"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.671
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.664
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
trust_remote_code: True
|
||||
@@ -1,12 +0,0 @@
|
||||
# For hf script, without -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m nm-testing/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform -b auto -l 1000 -f 5
|
||||
model_name: "nm-testing/Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.905
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.905
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For hf script, without -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m meta-llama/Meta-Llama-3-70B-Instruct -b 32 -l 250 -f 5
|
||||
model_name: "meta-llama/Meta-Llama-3-70B-Instruct"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.892
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.892
|
||||
limit: 250
|
||||
num_fewshot: 5
|
||||
-12
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors -b auto -l 1000 -f 5 -t 1
|
||||
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-W8A8-FP8-Channelwise-compressed-tensors"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.752
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.754
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform -b auto -l 1000 -f 5 -t 1
|
||||
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-FBGEMM-nonuniform"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.753
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.753
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
-12
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test -b 32 -l 1000 -f 5 -t 1
|
||||
model_name: "nm-testing/Meta-Llama-3-8B-FP8-compressed-tensors-test"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.755
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.755
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Meta-Llama-3-8B-Instruct-FP8 -b 32 -l 250 -f 5 -t 1
|
||||
model_name: "neuralmagic/Meta-Llama-3-8B-Instruct-FP8"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.753
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.753
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
-12
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test -b "auto" -l 250 -f 5 -t 1
|
||||
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Asym-Per-Token-Test"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.764
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.764
|
||||
limit: 250
|
||||
num_fewshot: 5
|
||||
-12
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test -b "auto" -l 250 -f 5 -t 1
|
||||
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-W8-Channel-A8-Dynamic-Per-Token-Test"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.728
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.728
|
||||
limit: 250
|
||||
num_fewshot: 5
|
||||
-12
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test -b auto -l 1000 -f 5 -t 1
|
||||
model_name: "nm-testing/Meta-Llama-3-8B-Instruct-nonuniform-test"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.758
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.759
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For hf script, without -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m meta-llama/Meta-Llama-3-8B-Instruct -b 32 -l 250 -f 5
|
||||
model_name: "meta-llama/Meta-Llama-3-8B-Instruct"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.756
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.752
|
||||
limit: 250
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m HandH1998/QQQ-Llama-3-8b-g128 -b 32 -l 1000 -f 5 -t 1
|
||||
model_name: "HandH1998/QQQ-Llama-3-8b-g128"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.419
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.416
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
-11
@@ -1,11 +0,0 @@
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m RedHatAI/Llama-3.2-1B-Instruct-FP8 -b "auto" -l 1319 -f 5 -t 1
|
||||
model_name: "RedHatAI/Llama-3.2-1B-Instruct-FP8"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.335
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.323
|
||||
limit: 1319
|
||||
num_fewshot: 5
|
||||
-12
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8 -b "auto" -l 1000 -f 5 -t 1
|
||||
model_name: "neuralmagic/Llama-3.2-1B-Instruct-quantized.w8a8"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.356
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.358
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
-12
@@ -1,12 +0,0 @@
|
||||
# For hf script, without -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-chartqa-vllm-vlm-baseline.sh -m meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 -l 100 -t 8
|
||||
model_name: "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
|
||||
backend: "vllm-vlm"
|
||||
tasks:
|
||||
- name: "chartqa"
|
||||
metrics:
|
||||
- name: "relaxed_accuracy,none"
|
||||
# TODO(zhewenl): model card is 0.90, but the actual score is 0.80.
|
||||
value: 0.80
|
||||
limit: 100
|
||||
num_fewshot: 0
|
||||
@@ -1,15 +0,0 @@
|
||||
# For hf script, without -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-mmlupro-vllm-baseline.sh -m meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8 -l 250 -t 8 -f 5
|
||||
model_name: "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8"
|
||||
rocm_safetensors_load_strategy: lazy
|
||||
required_gpu_arch:
|
||||
- gfx942
|
||||
- gfx950
|
||||
tasks:
|
||||
- name: "mmlu_pro"
|
||||
metrics:
|
||||
- name: "exact_match,custom-extract"
|
||||
value: 0.80
|
||||
limit: 250 # will run on 250 * 14 subjects = 3500 samples
|
||||
num_fewshot: 5
|
||||
rtol: 0.05
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m mgoin/Minitron-4B-Base-FP8 -b auto -l 1000 -f 5 -t 1
|
||||
model_name: "mgoin/Minitron-4B-Base-FP8"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.231
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.22
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Mixtral-8x22B-Instruct-v0.1-FP8-dynamic -b "auto" -l 250 -f 5 -t 8
|
||||
model_name: "neuralmagic/Mixtral-8x22B-Instruct-v0.1-FP8-dynamic"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.86
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.86
|
||||
limit: 250
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Mixtral-8x7B-Instruct-v0.1-FP8 -b "auto" -l 250 -f 5 -t 4
|
||||
model_name: "neuralmagic/Mixtral-8x7B-Instruct-v0.1-FP8"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.624
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.624
|
||||
limit: 250
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For hf script, without -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-hf-baseline.sh -m neuralmagic/Mixtral-8x7B-Instruct-v0.1 -b 32 -l 250 -f 5
|
||||
model_name: "mistralai/Mixtral-8x7B-Instruct-v0.1"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.616
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.632
|
||||
limit: 250
|
||||
num_fewshot: 5
|
||||
@@ -1,15 +0,0 @@
|
||||
model_name: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-BF16"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.695
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.447
|
||||
limit: 1319
|
||||
num_fewshot: 5
|
||||
max_model_len: 262144
|
||||
enforce_eager: false
|
||||
apply_chat_template: true
|
||||
fewshot_as_multiturn: true
|
||||
trust_remote_code: true
|
||||
@@ -1,17 +0,0 @@
|
||||
model_name: "nvidia/NVIDIA-Nemotron-3-Nano-30B-A3B-FP8"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.7142
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.4579
|
||||
moe_backend: "flashinfer_cutlass"
|
||||
limit: 1319
|
||||
num_fewshot: 5
|
||||
max_model_len: 262144
|
||||
kv_cache_dtype: fp8
|
||||
enforce_eager: false
|
||||
apply_chat_template: true
|
||||
fewshot_as_multiturn: true
|
||||
trust_remote_code: true
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16 -b auto -l 1319 -f 5 -t 1
|
||||
model_name: "nm-testing/Qwen1.5-MoE-A2.7B-Chat-quantized.w4a16"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.30
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.465
|
||||
limit: 1319
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen2-1.5B-Instruct-FP8W8 -b auto -l 1000 -f 5 -t 1
|
||||
model_name: "nm-testing/Qwen2-1.5B-Instruct-FP8W8"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.578
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.585
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8 -b "auto" -l 1000 -f 5 -t 1
|
||||
model_name: "neuralmagic/Qwen2-1.5B-Instruct-quantized.w8a8"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.593
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.588
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash ./run-lm-eval-gsm-vllm-baseline.sh -m Qwen/Qwen2-57B-A14B-Instruct -b "auto" -l 250 -f 5 -t 4
|
||||
model_name: "Qwen/Qwen2-57B-A14B-Instruct"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.792
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.824
|
||||
limit: 250
|
||||
num_fewshot: 5
|
||||
@@ -1,11 +0,0 @@
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m Qwen/Qwen2.5-1.5B-Instruct -b auto -l 1319 -f 5 -t 1
|
||||
model_name: "Qwen/Qwen2.5-1.5B-Instruct"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.54
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.59
|
||||
limit: 1319
|
||||
num_fewshot: 5
|
||||
@@ -1,15 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size)
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic -l 1319 -t 1
|
||||
model_name: "RedHatAI/Qwen2.5-VL-3B-Instruct-FP8-Dynamic"
|
||||
required_gpu_arch:
|
||||
- gfx942
|
||||
- gfx950
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.47
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.64
|
||||
limit: 1319
|
||||
num_fewshot: 5
|
||||
@@ -1,12 +0,0 @@
|
||||
# For vllm script, with -t option (tensor parallel size).
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-chartqa-vllm-vlm-baseline.sh -m Qwen/Qwen2.5-VL-7B-Instruct -l 2500 -t 1
|
||||
|
||||
model_name: "Qwen/Qwen2.5-VL-7B-Instruct"
|
||||
backend: "vllm-vlm"
|
||||
tasks:
|
||||
- name: "chartqa"
|
||||
metrics:
|
||||
- name: "relaxed_accuracy,none"
|
||||
value: 0.855
|
||||
limit: 2500
|
||||
num_fewshot: 0
|
||||
@@ -1,17 +0,0 @@
|
||||
model_name: "Qwen/Qwen3-235B-A22B-Instruct-2507-FP8"
|
||||
required_gpu_arch:
|
||||
- gfx942
|
||||
- gfx950
|
||||
tasks:
|
||||
- name: "mmlu_pro"
|
||||
metrics:
|
||||
- name: "exact_match,custom-extract"
|
||||
value: 0.82
|
||||
limit: 250 # will run on 250 * 14 subjects = 3500 samples
|
||||
num_fewshot: 5
|
||||
enforce_eager: false # we use false to speed up the eval process
|
||||
kv_cache_dtype: fp8 # we use fp8 to speed up the eval process
|
||||
max_model_len: 40960
|
||||
apply_chat_template: true
|
||||
fewshot_as_multiturn: true
|
||||
gen_kwargs: "temperature=0,top_p=1,top_k=0,max_gen_toks=5632,until=<|ENDANSWER|>"
|
||||
@@ -1,2 +0,0 @@
|
||||
Qwen3-235B-A22B-Instruct-2507-FP8.yaml
|
||||
NVIDIA-Nemotron-3-Nano-30B-A3B-FP8.yaml
|
||||
@@ -1 +0,0 @@
|
||||
Qwen3-235B-A22B-Instruct-2507-FP8.yaml
|
||||
@@ -1 +0,0 @@
|
||||
Meta-Llama-4-Maverick-17B-128E-Instruct-FP8.yaml
|
||||
@@ -1,6 +0,0 @@
|
||||
Meta-Llama-3-70B-Instruct-FBGEMM-nonuniform.yaml
|
||||
Meta-Llama-3-70B-Instruct.yaml
|
||||
Mixtral-8x7B-Instruct-v0.1.yaml
|
||||
Qwen2-57B-A14-Instruct.yaml
|
||||
DeepSeek-V2-Lite-Chat.yaml
|
||||
NVIDIA-Nemotron-3-Nano-30B-A3B-BF16.yaml
|
||||
@@ -1 +0,0 @@
|
||||
Meta-Llama-4-Maverick-17B-128E-Instruct-FP8-MM.yaml
|
||||
@@ -1 +0,0 @@
|
||||
Qwen2.5-VL-7B-Instruct.yaml
|
||||
@@ -1,6 +0,0 @@
|
||||
Qwen2.5-1.5B-Instruct.yaml
|
||||
Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml
|
||||
Meta-Llama-3-8B-Instruct-INT8-compressed-tensors-asym.yaml
|
||||
Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml
|
||||
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
|
||||
Qwen1.5-MoE-W4A16-compressed-tensors.yaml
|
||||
@@ -1,6 +0,0 @@
|
||||
Qwen2.5-1.5B-Instruct.yaml
|
||||
Meta-Llama-3.2-1B-Instruct-INT8-compressed-tensors.yaml
|
||||
Meta-Llama-3-8B-Instruct-INT8-compressed-tensors-asym.yaml
|
||||
Meta-Llama-3-8B-Instruct-nonuniform-compressed-tensors.yaml
|
||||
Qwen2.5-VL-3B-Instruct-FP8-dynamic.yaml
|
||||
Qwen1.5-MoE-W4A16-compressed-tensors.yaml
|
||||
@@ -1,44 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
def pytest_addoption(parser):
|
||||
parser.addoption(
|
||||
"--config-list-file",
|
||||
action="store",
|
||||
help="Path to the file listing model config YAMLs (one per line)",
|
||||
)
|
||||
parser.addoption(
|
||||
"--tp-size",
|
||||
action="store",
|
||||
default="1",
|
||||
help="Tensor parallel size to use for evaluation",
|
||||
)
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def config_list_file(pytestconfig, config_dir):
|
||||
rel_path = pytestconfig.getoption("--config-list-file")
|
||||
return config_dir / rel_path
|
||||
|
||||
|
||||
@pytest.fixture(scope="session")
|
||||
def tp_size(pytestconfig):
|
||||
return pytestconfig.getoption("--tp-size")
|
||||
|
||||
|
||||
def pytest_generate_tests(metafunc):
|
||||
if "config_filename" in metafunc.fixturenames:
|
||||
rel_path = metafunc.config.getoption("--config-list-file")
|
||||
config_list_file = Path(rel_path).resolve()
|
||||
config_dir = config_list_file.parent
|
||||
with open(config_list_file, encoding="utf-8") as f:
|
||||
configs = [
|
||||
config_dir / line.strip()
|
||||
for line in f
|
||||
if line.strip() and not line.startswith("#")
|
||||
]
|
||||
metafunc.parametrize("config_filename", configs)
|
||||
@@ -1,44 +0,0 @@
|
||||
#!/bin/bash
|
||||
# We can use this script to compute baseline accuracy on chartqa for vllm.
|
||||
#
|
||||
# Make sure you have lm-eval-harness installed:
|
||||
# pip install "lm-eval[api]>=0.4.12"
|
||||
|
||||
usage() {
|
||||
echo``
|
||||
echo "Runs lm eval harness on ChartQA using multimodal vllm."
|
||||
echo "This pathway is intended to be used to create baselines for "
|
||||
echo "our correctness tests in vllm's CI."
|
||||
echo
|
||||
echo "usage: ${0} <options>"
|
||||
echo
|
||||
echo " -m - huggingface stub or local directory of the model"
|
||||
echo " -l - limit number of samples to run"
|
||||
echo " -t - tensor parallel size to run at"
|
||||
echo
|
||||
}
|
||||
|
||||
while getopts "m:l:t:" OPT; do
|
||||
case ${OPT} in
|
||||
m )
|
||||
MODEL="$OPTARG"
|
||||
;;
|
||||
l )
|
||||
LIMIT="$OPTARG"
|
||||
;;
|
||||
t )
|
||||
TP_SIZE="$OPTARG"
|
||||
;;
|
||||
\? )
|
||||
usage
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
lm_eval --model vllm-vlm \
|
||||
--model_args "pretrained=$MODEL,tensor_parallel_size=$TP_SIZE" \
|
||||
--tasks chartqa \
|
||||
--batch_size auto \
|
||||
--apply_chat_template \
|
||||
--limit "$LIMIT"
|
||||
@@ -1,46 +0,0 @@
|
||||
#!/bin/bash
|
||||
# We can use this script to compute baseline accuracy on GSM for transformers.
|
||||
#
|
||||
# Make sure you have lm-eval-harness installed:
|
||||
# pip install "lm-eval[api]>=0.4.12"
|
||||
|
||||
usage() {
|
||||
echo``
|
||||
echo "Runs lm eval harness on GSM8k using huggingface transformers."
|
||||
echo "This pathway is intended to be used to create baselines for "
|
||||
echo "our automated nm-test-accuracy workflow"
|
||||
echo
|
||||
echo "usage: ${0} <options>"
|
||||
echo
|
||||
echo " -m - huggingface stub or local directory of the model"
|
||||
echo " -b - batch size to run the evaluation at"
|
||||
echo " -l - limit number of samples to run"
|
||||
echo " -f - number of fewshot samples to use"
|
||||
echo
|
||||
}
|
||||
|
||||
while getopts "m:b:l:f:" OPT; do
|
||||
case ${OPT} in
|
||||
m )
|
||||
MODEL="$OPTARG"
|
||||
;;
|
||||
b )
|
||||
BATCH_SIZE="$OPTARG"
|
||||
;;
|
||||
l )
|
||||
LIMIT="$OPTARG"
|
||||
;;
|
||||
f )
|
||||
FEWSHOT="$OPTARG"
|
||||
;;
|
||||
\? )
|
||||
usage
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
lm_eval --model hf \
|
||||
--model_args "pretrained=$MODEL,parallelize=True" \
|
||||
--tasks gsm8k --num_fewshot "$FEWSHOT" --limit "$LIMIT" \
|
||||
--batch_size "$BATCH_SIZE"
|
||||
@@ -1,51 +0,0 @@
|
||||
#!/bin/bash
|
||||
# We can use this script to compute baseline accuracy on GSM for vllm.
|
||||
# We use this for fp8, which HF does not support.
|
||||
#
|
||||
# Make sure you have lm-eval-harness installed:
|
||||
# pip install "lm-eval[api]>=0.4.12"
|
||||
|
||||
usage() {
|
||||
echo``
|
||||
echo "Runs lm eval harness on GSM8k using huggingface transformers."
|
||||
echo "This pathway is intended to be used to create baselines for "
|
||||
echo "our automated nm-test-accuracy workflow"
|
||||
echo
|
||||
echo "usage: ${0} <options>"
|
||||
echo
|
||||
echo " -m - huggingface stub or local directory of the model"
|
||||
echo " -b - batch size to run the evaluation at"
|
||||
echo " -l - limit number of samples to run"
|
||||
echo " -f - number of fewshot samples to use"
|
||||
echo " -t - tensor parallel size to run at"
|
||||
echo
|
||||
}
|
||||
|
||||
while getopts "m:b:l:f:t:" OPT; do
|
||||
case ${OPT} in
|
||||
m )
|
||||
MODEL="$OPTARG"
|
||||
;;
|
||||
b )
|
||||
BATCH_SIZE="$OPTARG"
|
||||
;;
|
||||
l )
|
||||
LIMIT="$OPTARG"
|
||||
;;
|
||||
f )
|
||||
FEWSHOT="$OPTARG"
|
||||
;;
|
||||
t )
|
||||
TP_SIZE="$OPTARG"
|
||||
;;
|
||||
\? )
|
||||
usage
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
lm_eval --model vllm \
|
||||
--model_args "pretrained=$MODEL,tensor_parallel_size=$TP_SIZE,add_bos_token=true,trust_remote_code=true,max_model_len=4096" \
|
||||
--tasks gsm8k --num_fewshot "$FEWSHOT" --limit "$LIMIT" \
|
||||
--batch_size "$BATCH_SIZE"
|
||||
@@ -1,47 +0,0 @@
|
||||
#!/bin/bash
|
||||
# We can use this script to compute baseline accuracy on MMLUPRO for vllm.
|
||||
# We use this for fp8, which HF does not support.
|
||||
#
|
||||
# Make sure you have lm-eval-harness installed:
|
||||
# pip install "lm-eval[api]>=0.4.12"
|
||||
|
||||
usage() {
|
||||
echo``
|
||||
echo "Runs lm eval harness on MMLU Pro using huggingface transformers."
|
||||
echo "This pathway is intended to be used to create baselines for "
|
||||
echo "our automated nm-test-accuracy workflow"
|
||||
echo
|
||||
echo "usage: ${0} <options>"
|
||||
echo
|
||||
echo " -m - huggingface stub or local directory of the model"
|
||||
echo " -l - limit number of samples to run"
|
||||
echo " -f - number of fewshot samples to use"
|
||||
echo " -t - tensor parallel size to run at"
|
||||
echo
|
||||
}
|
||||
|
||||
while getopts "m:l:f:t:" OPT; do
|
||||
case ${OPT} in
|
||||
m )
|
||||
MODEL="$OPTARG"
|
||||
;;
|
||||
l )
|
||||
LIMIT="$OPTARG"
|
||||
;;
|
||||
f )
|
||||
FEWSHOT="$OPTARG"
|
||||
;;
|
||||
t )
|
||||
TP_SIZE="$OPTARG"
|
||||
;;
|
||||
\? )
|
||||
usage
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
lm_eval --model vllm \
|
||||
--model_args "pretrained=$MODEL,tensor_parallel_size=$TP_SIZE,add_bos_token=true,trust_remote_code=true,max_model_len=4096" \
|
||||
--tasks mmlu_pro --num_fewshot "$FEWSHOT" --limit "$LIMIT" \
|
||||
--batch_size auto
|
||||
@@ -1,154 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
LM eval harness on model to compare vs HF baseline computed offline.
|
||||
Configs are found in configs/$MODEL.yaml
|
||||
|
||||
pytest -s -v test_lm_eval_correctness.py \
|
||||
--config-list-file=configs/models-small.txt \
|
||||
--tp-size=1
|
||||
"""
|
||||
|
||||
import os
|
||||
from contextlib import contextmanager
|
||||
|
||||
import lm_eval
|
||||
import pytest
|
||||
import yaml
|
||||
|
||||
from vllm.platforms import current_platform
|
||||
|
||||
DEFAULT_RTOL = 0.08
|
||||
|
||||
|
||||
@contextmanager
|
||||
def scoped_env_vars(new_env: dict[str, str]):
|
||||
if not new_env:
|
||||
# Fast path: nothing to do
|
||||
yield
|
||||
return
|
||||
|
||||
old_values = {}
|
||||
new_keys = []
|
||||
|
||||
try:
|
||||
for key, value in new_env.items():
|
||||
if key in os.environ:
|
||||
old_values[key] = os.environ[key]
|
||||
else:
|
||||
new_keys.append(key)
|
||||
os.environ[key] = str(value)
|
||||
yield
|
||||
finally:
|
||||
# Restore / clean up
|
||||
for key, value in old_values.items():
|
||||
os.environ[key] = value
|
||||
for key in new_keys:
|
||||
os.environ.pop(key, None)
|
||||
|
||||
|
||||
def launch_lm_eval(eval_config, tp_size):
|
||||
trust_remote_code = eval_config.get("trust_remote_code", False)
|
||||
max_model_len = eval_config.get("max_model_len", 4096)
|
||||
batch_size = eval_config.get("batch_size", "auto")
|
||||
backend = eval_config.get("backend", "vllm")
|
||||
enforce_eager = eval_config.get("enforce_eager", "true")
|
||||
kv_cache_dtype = eval_config.get("kv_cache_dtype", "auto")
|
||||
model_args = (
|
||||
f"pretrained={eval_config['model_name']},"
|
||||
f"tensor_parallel_size={tp_size},"
|
||||
f"enforce_eager={enforce_eager},"
|
||||
f"kv_cache_dtype={kv_cache_dtype},"
|
||||
f"add_bos_token=true,"
|
||||
f"trust_remote_code={trust_remote_code},"
|
||||
f"max_model_len={max_model_len},"
|
||||
"allow_deprecated_quantization=True,"
|
||||
)
|
||||
|
||||
if current_platform.is_rocm() and "Nemotron-3" in eval_config["model_name"]:
|
||||
model_args += "attention_backend=TRITON_ATTN"
|
||||
|
||||
moe_backend = eval_config.get("moe_backend", None)
|
||||
if moe_backend is not None:
|
||||
model_args += f"moe_backend={moe_backend},"
|
||||
|
||||
if current_platform.is_rocm():
|
||||
rocm_load_strategy = eval_config.get("rocm_safetensors_load_strategy")
|
||||
if rocm_load_strategy is not None:
|
||||
model_args += f"safetensors_load_strategy={rocm_load_strategy},"
|
||||
|
||||
env_vars = eval_config.get("env_vars", None)
|
||||
with scoped_env_vars(env_vars):
|
||||
results = lm_eval.simple_evaluate(
|
||||
model=backend,
|
||||
model_args=model_args,
|
||||
tasks=[task["name"] for task in eval_config["tasks"]],
|
||||
num_fewshot=eval_config["num_fewshot"],
|
||||
limit=eval_config["limit"],
|
||||
# TODO(yeq): using chat template w/ fewshot_as_multiturn is supposed help
|
||||
# text models. however, this is regressing measured strict-match for
|
||||
# existing text models in CI, so only apply it for mm, or explicitly set
|
||||
apply_chat_template=eval_config.get(
|
||||
"apply_chat_template", backend == "vllm-vlm"
|
||||
),
|
||||
fewshot_as_multiturn=eval_config.get("fewshot_as_multiturn", False),
|
||||
# Forward decoding and early-stop controls (e.g., max_gen_toks, until=...)
|
||||
gen_kwargs=eval_config.get("gen_kwargs"),
|
||||
batch_size=batch_size,
|
||||
)
|
||||
return results
|
||||
|
||||
|
||||
def _check_rocm_gpu_arch_requirement(eval_config):
|
||||
"""Skip the test if the model requires a ROCm GPU arch not present.
|
||||
|
||||
Model YAML configs can specify::
|
||||
|
||||
required_gpu_arch:
|
||||
- gfx942
|
||||
- gfx950
|
||||
|
||||
The check only applies on ROCm. On other platforms (e.g. CUDA) the
|
||||
field is ignored so that shared config files work for both NVIDIA and
|
||||
AMD CI pipelines.
|
||||
"""
|
||||
required_archs = eval_config.get("required_gpu_arch")
|
||||
if not required_archs:
|
||||
return
|
||||
|
||||
if not current_platform.is_rocm():
|
||||
return
|
||||
|
||||
from vllm.platforms.rocm import _GCN_ARCH # noqa: E402
|
||||
|
||||
if not any(arch in _GCN_ARCH for arch in required_archs):
|
||||
pytest.skip(
|
||||
f"Model requires GPU arch {required_archs}, "
|
||||
f"but detected arch is '{_GCN_ARCH}'"
|
||||
)
|
||||
|
||||
|
||||
def test_lm_eval_correctness_param(config_filename, tp_size):
|
||||
eval_config = yaml.safe_load(config_filename.read_text(encoding="utf-8"))
|
||||
|
||||
_check_rocm_gpu_arch_requirement(eval_config)
|
||||
|
||||
results = launch_lm_eval(eval_config, tp_size)
|
||||
|
||||
rtol = eval_config.get("rtol", DEFAULT_RTOL)
|
||||
|
||||
success = True
|
||||
for task in eval_config["tasks"]:
|
||||
for metric in task["metrics"]:
|
||||
ground_truth = metric["value"]
|
||||
measured_value = results["results"][task["name"]][metric["name"]]
|
||||
print(
|
||||
f"{task['name']} | {metric['name']}: "
|
||||
f"ground_truth={ground_truth:.3f} | "
|
||||
f"measured={measured_value:.3f} | rtol={rtol}"
|
||||
)
|
||||
|
||||
min_acceptable = ground_truth * (1 - rtol)
|
||||
success = success and measured_value >= min_acceptable
|
||||
|
||||
assert success
|
||||
@@ -1,180 +0,0 @@
|
||||
# vLLM benchmark suite
|
||||
|
||||
## Introduction
|
||||
|
||||
This directory contains a benchmarking suite for **developers** to run locally and gain clarity on whether their PR improves/degrades vllm's performance.
|
||||
vLLM also maintains a continuous performance benchmark under [perf.vllm.ai](https://perf.vllm.ai/), hosted under PyTorch CI HUD.
|
||||
|
||||
## Performance benchmark quick overview
|
||||
|
||||
**Benchmarking Coverage**: latency, throughput and fix-qps serving on B200, A100, H100, Intel® Xeon® Processors, Intel® Gaudi® 3 Accelerators and Arm® Neoverse™ with different models.
|
||||
|
||||
**Benchmarking Duration**: about 1hr.
|
||||
|
||||
**For benchmarking developers**: please try your best to constraint the duration of benchmarking to about 1 hr so that it won't take forever to run.
|
||||
|
||||
## Trigger the benchmark
|
||||
|
||||
The benchmark needs to be triggered manually:
|
||||
|
||||
```bash
|
||||
bash .buildkite/performance-benchmarks/scripts/run-performance-benchmarks.sh
|
||||
```
|
||||
|
||||
Runtime environment variables:
|
||||
|
||||
- `ON_CPU`: set the value to '1' on Intel® Xeon® and Arm® Neoverse™ Processors. Default value is 0.
|
||||
- `SERVING_JSON`: JSON file to use for the serving tests. Default value is empty string (use default file).
|
||||
- `LATENCY_JSON`: JSON file to use for the latency tests. Default value is empty string (use default file).
|
||||
- `THROUGHPUT_JSON`: JSON file to use for the throughout tests. Default value is empty string (use default file).
|
||||
- `REMOTE_HOST`: IP for the remote vLLM service to benchmark. Default value is empty string.
|
||||
- `REMOTE_PORT`: Port for the remote vLLM service to benchmark. Default value is empty string.
|
||||
|
||||
## Performance benchmark details
|
||||
|
||||
See [performance-benchmarks-descriptions.md](performance-benchmarks-descriptions.md) for detailed descriptions, and use `tests/latency-tests.json`, `tests/throughput-tests.json`, `tests/serving-tests.json` to configure the test cases.
|
||||
> NOTE: For Intel® Xeon® Processors, use `tests/latency-tests-cpu.json`, `tests/throughput-tests-cpu.json`, `tests/serving-tests-cpu.json` instead.
|
||||
> For Intel® Gaudi® 3 Accelerators, use `tests/latency-tests-hpu.json`, `tests/throughput-tests-hpu.json`, `tests/serving-tests-hpu.json` instead.
|
||||
> For Arm® Neoverse™, use `tests/latency-tests-arm64-cpu.json`, `tests/throughput-tests-arm64-cpu.json`, `tests/serving-tests-arm64-cpu.json` instead.
|
||||
|
||||
### Latency test
|
||||
|
||||
Here is an example of one test inside `latency-tests.json`:
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"test_name": "latency_llama8B_tp1",
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-8B",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"num_iters_warmup": 5,
|
||||
"num_iters": 15
|
||||
}
|
||||
},
|
||||
]
|
||||
```
|
||||
|
||||
In this example:
|
||||
|
||||
- The `test_name` attributes is a unique identifier for the test. In `latency-tests.json`, it must start with `latency_`.
|
||||
- The `parameters` attribute control the command line arguments to be used for `vllm bench latency`. Note that please use underline `_` instead of the dash `-` when specifying the command line arguments, and `run-performance-benchmarks.sh` will convert the underline to dash when feeding the arguments to `vllm bench latency`. For example, the corresponding command line arguments for `vllm bench latency` will be `--model meta-llama/Meta-Llama-3-8B --tensor-parallel-size 1 --load-format dummy --num-iters-warmup 5 --num-iters 15`
|
||||
|
||||
Note that the performance numbers are highly sensitive to the value of the parameters. Please make sure the parameters are set correctly.
|
||||
|
||||
WARNING: The benchmarking script will save json results by itself, so please do not configure `--output-json` parameter in the json file.
|
||||
|
||||
### Throughput test
|
||||
|
||||
The tests are specified in `throughput-tests.json`. The syntax is similar to `latency-tests.json`, except for that the parameters will be fed forward to `vllm bench throughput`.
|
||||
|
||||
The number of this test is also stable -- a slight change on the value of this number might vary the performance numbers by a lot.
|
||||
|
||||
### Serving test
|
||||
|
||||
We test the throughput by using `vllm bench serve` with request rate = inf to cover the online serving overhead. The corresponding parameters are in `serving-tests.json`, and here is an example:
|
||||
|
||||
```json
|
||||
[
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_sharegpt",
|
||||
"qps_list": [1, 4, 16, "inf"],
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-8B",
|
||||
"tensor_parallel_size": 1,
|
||||
"disable_log_stats": "",
|
||||
"load_format": "dummy"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-8B",
|
||||
"backend": "vllm",
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
]
|
||||
```
|
||||
|
||||
Inside this example:
|
||||
|
||||
- The `test_name` attribute is also a unique identifier for the test. It must start with `serving_`.
|
||||
- The `server-parameters` includes the command line arguments for vLLM server.
|
||||
- The `client-parameters` includes the command line arguments for `vllm bench serve`.
|
||||
- The `qps_list` controls the list of qps for test. It will be used to configure the `--request-rate` parameter in `vllm bench serve`
|
||||
|
||||
The number of this test is less stable compared to the delay and latency benchmarks (due to randomized sharegpt dataset sampling inside `benchmark_serving.py`), but a large change on this number (e.g. 5% change) still vary the output greatly.
|
||||
|
||||
WARNING: The benchmarking script will save json results by itself, so please do not configure `--save-results` or other results-saving-related parameters in `serving-tests.json`.
|
||||
|
||||
#### Default Parameters Field
|
||||
|
||||
We can specify default parameters in a JSON field with key `defaults`. Parameters defined in the field are applied globally to all serving tests, and can be overridden in test case fields. Here is an example:
|
||||
|
||||
<details>
|
||||
<summary> An Example of default parameters field </summary>
|
||||
|
||||
```json
|
||||
{
|
||||
"defaults": {
|
||||
"qps_list": [
|
||||
"inf"
|
||||
],
|
||||
"server_environment_variables": {
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1
|
||||
},
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1,
|
||||
"dtype": "bfloat16",
|
||||
"block_size": 128,
|
||||
"disable_log_stats": "",
|
||||
"load_format": "dummy"
|
||||
},
|
||||
"client_parameters": {
|
||||
"backend": "vllm",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128,
|
||||
"num_prompts": 200,
|
||||
"ignore-eos": ""
|
||||
}
|
||||
},
|
||||
"tests": [
|
||||
{
|
||||
"test_name": "serving_llama3B_tp2_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-3.2-3B-Instruct",
|
||||
"tensor_parallel_size": 2,
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-3.2-3B-Instruct",
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_qwen3_tp4_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "Qwen/Qwen3-14B",
|
||||
"tensor_parallel_size": 4,
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "Qwen/Qwen3-14B",
|
||||
}
|
||||
},
|
||||
]
|
||||
}
|
||||
```
|
||||
|
||||
</details>
|
||||
|
||||
### Visualizing the results
|
||||
|
||||
The `convert-results-json-to-markdown.py` helps you put the benchmarking results inside a markdown table, by formatting [descriptions.md](performance-benchmarks-descriptions.md) with real benchmarking results.
|
||||
You can find the result presented as a table inside the `buildkite/performance-benchmark` job page.
|
||||
If you do not see the table, please wait till the benchmark finish running.
|
||||
The json version of the table (together with the json version of the benchmark) will be also attached to the markdown file.
|
||||
The raw benchmarking results (in the format of json files) are in the `Artifacts` tab of the benchmarking.
|
||||
|
||||
#### Performance Results Comparison
|
||||
|
||||
Follow the instructions in [performance results comparison](https://docs.vllm.ai/en/latest/benchmarking/dashboard/#performance-results-comparison) to analyze performance results and the sizing guide.
|
||||
@@ -1,65 +0,0 @@
|
||||
# Performance benchmarks descriptions
|
||||
|
||||
## Latency tests
|
||||
|
||||
- Input length: 32 tokens.
|
||||
- Output length: 128 tokens.
|
||||
- Batch size: fixed (8).
|
||||
- GPU/HPU Models: llama-3.1 8B, llama-3 70B, mixtral 8x7B.
|
||||
- CPU Models: llama-3.1 8B.
|
||||
- Evaluation metrics: end-to-end latency (mean, median, p99).
|
||||
|
||||
{latency_tests_markdown_table}
|
||||
|
||||
## Throughput tests
|
||||
|
||||
- Input length: randomly sample 200 prompts from ShareGPT dataset (with fixed random seed).
|
||||
- Output length: the corresponding output length of these 200 prompts.
|
||||
- Batch size: dynamically determined by vllm to achieve maximum throughput.
|
||||
- GPU/HPU Models: llama-3.1 8B, llama-3 70B, mixtral 8x7B.
|
||||
- CPU Models: llama-3.1 8B.
|
||||
- Evaluation metrics: throughput.
|
||||
|
||||
{throughput_tests_markdown_table}
|
||||
|
||||
## Serving tests
|
||||
|
||||
- Input length: randomly sample 200 prompts from ShareGPT dataset (with fixed random seed).
|
||||
- Output length: the corresponding output length of these 200 prompts.
|
||||
- Batch size: dynamically determined by vllm and the arrival pattern of the requests.
|
||||
- **Average QPS (query per second)**: 1, 4, 16 and inf. QPS = inf means all requests come at once. For other QPS values, the arrival time of each query is determined using a random Poisson process (with fixed random seed).
|
||||
- GPU/HPU Models: llama-3.1 8B, llama-3 70B, mixtral 8x7B.
|
||||
- We also added a speculative decoding test for llama-3 70B on GPU, under QPS 2
|
||||
- CPU Models: llama-3.1 8B.
|
||||
- Evaluation metrics: throughput, TTFT (time to the first token, with mean, median and p99), ITL (inter-token latency, with mean, median and p99).
|
||||
- For CPU, we added random dataset tests to benchmark fixed input/output length with 100 prompts.
|
||||
|
||||
{serving_tests_markdown_table}
|
||||
|
||||
## Platform Information
|
||||
|
||||
{platform_markdown_table}
|
||||
|
||||
## json version of the benchmarking tables
|
||||
|
||||
This section contains the data of the markdown tables above in JSON format.
|
||||
You can load the benchmarking tables into pandas dataframes as follows:
|
||||
|
||||
```python
|
||||
import json
|
||||
import pandas as pd
|
||||
|
||||
benchmarking_results_json = """The json string"""
|
||||
benchmarking_results = json.loads(benchmarking_results_json)
|
||||
latency_results = pd.DataFrame.from_dict(benchmarking_results["latency"])
|
||||
throughput_results = pd.DataFrame.from_dict(benchmarking_results["throughput"])
|
||||
serving_results = pd.DataFrame.from_dict(benchmarking_results["serving"])
|
||||
```
|
||||
|
||||
The json string for all benchmarking tables:
|
||||
|
||||
```json
|
||||
{benchmarking_results_in_json_string}
|
||||
```
|
||||
|
||||
You can also check the raw experiment data in the Artifact tab of the Buildkite page.
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,414 +0,0 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
|
||||
import argparse
|
||||
import json
|
||||
import os
|
||||
import shlex
|
||||
from importlib import util
|
||||
from pathlib import Path
|
||||
from typing import Any
|
||||
|
||||
import pandas as pd
|
||||
import psutil
|
||||
import regex as re
|
||||
from tabulate import tabulate
|
||||
|
||||
# latency results and the keys that will be printed into markdown
|
||||
latency_results = []
|
||||
latency_column_mapping = {
|
||||
"test_name": "Test name",
|
||||
"gpu_type": "GPU",
|
||||
"avg_latency": "Mean latency (ms)",
|
||||
# "P10": "P10 (s)",
|
||||
# "P25": "P25 (s)",
|
||||
"P50": "Median latency (ms)",
|
||||
# "P75": "P75 (s)",
|
||||
# "P90": "P90 (s)",
|
||||
"P99": "P99 latency (ms)",
|
||||
}
|
||||
|
||||
# throughput tests and the keys that will be printed into markdown
|
||||
throughput_results = []
|
||||
throughput_results_column_mapping = {
|
||||
"test_name": "Test name",
|
||||
"gpu_type": "GPU",
|
||||
"num_requests": "# of req.",
|
||||
"total_num_tokens": "Total # of tokens",
|
||||
"elapsed_time": "Elapsed time (s)",
|
||||
"requests_per_second": "Tput (req/s)",
|
||||
"tokens_per_second": "Tput (tok/s)",
|
||||
}
|
||||
|
||||
# serving results and the keys that will be printed into markdown
|
||||
serving_results = []
|
||||
serving_column_mapping = {
|
||||
"test_name": "Test name",
|
||||
"model_id": "Model",
|
||||
"dataset_name": "Dataset Name",
|
||||
"input_len": "Input Len",
|
||||
"output_len": "Output Len",
|
||||
"tp_size": "TP Size",
|
||||
"pp_size": "PP Size",
|
||||
"dtype": "dtype",
|
||||
"gpu_type": "GPU",
|
||||
"completed": "# of req.",
|
||||
"qps": "qps",
|
||||
"max_concurrency": "# of max concurrency.",
|
||||
"request_throughput": "Tput (req/s)",
|
||||
"total_token_throughput": "Total Token Tput (tok/s)",
|
||||
"output_throughput": "Output Tput (tok/s)",
|
||||
# "total_input_tokens": "Total input tokens",
|
||||
# "total_output_tokens": "Total output tokens",
|
||||
"mean_ttft_ms": "Mean TTFT (ms)",
|
||||
"median_ttft_ms": "Median TTFT (ms)",
|
||||
"p99_ttft_ms": "P99 TTFT (ms)",
|
||||
"std_ttft_ms": "STD TTFT (ms)",
|
||||
"mean_tpot_ms": "Mean TPOT (ms)",
|
||||
"median_tpot_ms": "Median",
|
||||
"p99_tpot_ms": "P99",
|
||||
"std_tpot_ms": "STD TPOT (ms)",
|
||||
"mean_itl_ms": "Mean ITL (ms)",
|
||||
"median_itl_ms": "Median ITL (ms)",
|
||||
"p99_itl_ms": "P99 ITL (ms)",
|
||||
}
|
||||
|
||||
|
||||
def read_markdown(file):
|
||||
if os.path.exists(file):
|
||||
with open(file) as f:
|
||||
return f.read() + "\n"
|
||||
else:
|
||||
return f"{file} not found.\n"
|
||||
|
||||
|
||||
def results_to_json(latency, throughput, serving):
|
||||
return json.dumps(
|
||||
{
|
||||
"latency": latency.to_dict(),
|
||||
"throughput": throughput.to_dict(),
|
||||
"serving": serving.to_dict(),
|
||||
}
|
||||
)
|
||||
|
||||
|
||||
def get_size_with_unit(bytes, suffix="B"):
|
||||
"""
|
||||
Scale bytes to its proper format
|
||||
e.g:
|
||||
1253656 => '1.20MB'
|
||||
1253656678 => '1.17GB'
|
||||
"""
|
||||
factor = 1024
|
||||
for unit in ["", "K", "M", "G", "T", "P"]:
|
||||
if bytes < factor:
|
||||
return f"{bytes:.2f}{unit}{suffix}"
|
||||
bytes /= factor
|
||||
|
||||
|
||||
def _coerce(val: str) -> Any:
|
||||
"""Best-effort type coercion from string to Python types."""
|
||||
low = val.lower()
|
||||
if low == "null":
|
||||
return None
|
||||
if low == "true":
|
||||
return True
|
||||
if low == "false":
|
||||
return False
|
||||
# integers
|
||||
if re.fullmatch(r"[+-]?\d+", val):
|
||||
try:
|
||||
return int(val)
|
||||
except ValueError:
|
||||
pass
|
||||
# floats (keep 'inf'/'-inf'/'nan' as strings)
|
||||
if re.fullmatch(r"[+-]?\d*\.\d+", val):
|
||||
try:
|
||||
return float(val)
|
||||
except ValueError:
|
||||
pass
|
||||
return val
|
||||
|
||||
|
||||
def parse_client_command(cmd: str) -> dict[str, Any]:
|
||||
"""Parse the client_command shell string into {executable, script, args}."""
|
||||
toks = shlex.split(cmd)
|
||||
if len(toks) < 2:
|
||||
raise ValueError("client_command must include an executable and a script")
|
||||
executable, script = toks[0], toks[1]
|
||||
args: dict[str, Any] = {}
|
||||
|
||||
i = 2
|
||||
while i < len(toks):
|
||||
t = toks[i]
|
||||
if t.startswith("--"):
|
||||
# --key=value or --key (value) or boolean flag
|
||||
if "=" in t:
|
||||
key, val = t.split("=", 1)
|
||||
if key == "--metadata":
|
||||
md = {}
|
||||
if val:
|
||||
if "=" in val:
|
||||
k, v = val.split("=", 1)
|
||||
md[k] = _coerce(v)
|
||||
else:
|
||||
md[val] = True
|
||||
args[key] = md
|
||||
else:
|
||||
args[key] = _coerce(val)
|
||||
i += 1
|
||||
continue
|
||||
|
||||
key = t
|
||||
|
||||
# Special: consume metadata k=v pairs until next --flag
|
||||
if key == "--metadata":
|
||||
i += 1
|
||||
md = {}
|
||||
while i < len(toks) and not toks[i].startswith("--"):
|
||||
pair = toks[i]
|
||||
if "=" in pair:
|
||||
k, v = pair.split("=", 1)
|
||||
md[k] = _coerce(v)
|
||||
else:
|
||||
md[pair] = True
|
||||
i += 1
|
||||
args[key] = md
|
||||
continue
|
||||
|
||||
# Standard: check if next token is a value (not a flag)
|
||||
if i + 1 < len(toks) and not toks[i + 1].startswith("--"):
|
||||
args[key] = _coerce(toks[i + 1])
|
||||
i += 2
|
||||
else:
|
||||
# lone flag -> True
|
||||
args[key] = True
|
||||
i += 1
|
||||
else:
|
||||
# unexpected positional; skip
|
||||
i += 1
|
||||
|
||||
return {"executable": executable, "script": script, "args": args}
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser()
|
||||
parser.add_argument(
|
||||
"-r",
|
||||
"--result",
|
||||
type=str,
|
||||
default="results",
|
||||
help="Folder name for benchmark output results.",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
results_folder = Path(args.result)
|
||||
if not results_folder.exists():
|
||||
raise FileNotFoundError(f"results folder does not exist: {results_folder}")
|
||||
# collect results
|
||||
for test_file in results_folder.glob("*.json"):
|
||||
with open(test_file) as f:
|
||||
raw_result = json.loads(f.read())
|
||||
|
||||
if "serving" in str(test_file):
|
||||
# this result is generated via `vllm bench serve` command
|
||||
# attach the benchmarking command to raw_result
|
||||
try:
|
||||
with open(test_file.with_suffix(".commands")) as f:
|
||||
command = json.loads(f.read())
|
||||
except OSError as e:
|
||||
print(e)
|
||||
continue
|
||||
# Parse Server Command Arg
|
||||
out: dict[str, Any] = {
|
||||
"server_command": parse_client_command(command["server_command"])
|
||||
}
|
||||
parse_args = [
|
||||
"--tensor-parallel-size",
|
||||
"--pipeline-parallel-size",
|
||||
"--dtype",
|
||||
]
|
||||
col_mapping = ["tp_size", "pp_size", "dtype"]
|
||||
for index, arg in enumerate(parse_args):
|
||||
if arg in out["server_command"]["args"]:
|
||||
raw_result.update(
|
||||
{col_mapping[index]: out["server_command"]["args"][arg]}
|
||||
)
|
||||
|
||||
# Parse Client Command Arg
|
||||
out: dict[str, Any] = {
|
||||
"client_command": parse_client_command(command["client_command"])
|
||||
}
|
||||
parse_args = [
|
||||
"--dataset-name",
|
||||
"--random-input-len",
|
||||
"--random-output-len",
|
||||
"--request-rate",
|
||||
]
|
||||
col_mapping = ["dataset_name", "input_len", "output_len", "qps"]
|
||||
|
||||
for index, arg in enumerate(parse_args):
|
||||
if arg in out["client_command"]["args"]:
|
||||
raw_result.update(
|
||||
{col_mapping[index]: out["client_command"]["args"][arg]}
|
||||
)
|
||||
# Add Server, Client command
|
||||
raw_result.update(command)
|
||||
|
||||
# update the test name of this result
|
||||
raw_result.update({"test_name": test_file.stem})
|
||||
# add the result to raw_result
|
||||
serving_results.append(raw_result)
|
||||
continue
|
||||
|
||||
elif "latency" in f.name:
|
||||
# this result is generated via `vllm bench latency` command
|
||||
|
||||
# attach the benchmarking command to raw_result
|
||||
try:
|
||||
with open(test_file.with_suffix(".commands")) as f:
|
||||
command = json.loads(f.read())
|
||||
except OSError as e:
|
||||
print(e)
|
||||
continue
|
||||
|
||||
raw_result.update(command)
|
||||
|
||||
# update the test name of this result
|
||||
raw_result.update({"test_name": test_file.stem})
|
||||
|
||||
# get different percentiles
|
||||
for perc in [10, 25, 50, 75, 90, 99]:
|
||||
# Multiply 1000 to convert the time unit from s to ms
|
||||
raw_result.update(
|
||||
{f"P{perc}": 1000 * raw_result["percentiles"][str(perc)]}
|
||||
)
|
||||
raw_result["avg_latency"] = raw_result["avg_latency"] * 1000
|
||||
|
||||
# add the result to raw_result
|
||||
latency_results.append(raw_result)
|
||||
continue
|
||||
|
||||
elif "throughput" in f.name:
|
||||
# this result is generated via `vllm bench throughput` command
|
||||
|
||||
# attach the benchmarking command to raw_result
|
||||
try:
|
||||
with open(test_file.with_suffix(".commands")) as f:
|
||||
command = json.loads(f.read())
|
||||
except OSError as e:
|
||||
print(e)
|
||||
continue
|
||||
|
||||
raw_result.update(command)
|
||||
|
||||
# update the test name of this result
|
||||
raw_result.update({"test_name": test_file.stem})
|
||||
|
||||
# add the result to raw_result
|
||||
throughput_results.append(raw_result)
|
||||
continue
|
||||
|
||||
print(f"Skipping {test_file}")
|
||||
|
||||
latency_results = pd.DataFrame.from_dict(latency_results)
|
||||
serving_results = pd.DataFrame.from_dict(serving_results)
|
||||
throughput_results = pd.DataFrame.from_dict(throughput_results)
|
||||
|
||||
svmem = psutil.virtual_memory()
|
||||
platform_data = {
|
||||
"Physical cores": [psutil.cpu_count(logical=False)],
|
||||
"Total cores": [psutil.cpu_count(logical=True)],
|
||||
"Total Memory": [get_size_with_unit(svmem.total)],
|
||||
}
|
||||
|
||||
if util.find_spec("numa") is not None:
|
||||
from numa import info
|
||||
|
||||
platform_data["Total NUMA nodes"] = [info.get_num_configured_nodes()]
|
||||
|
||||
if util.find_spec("cpuinfo") is not None:
|
||||
from cpuinfo import get_cpu_info
|
||||
|
||||
platform_data["CPU Brand"] = [get_cpu_info()["brand_raw"]]
|
||||
|
||||
platform_results = pd.DataFrame.from_dict(
|
||||
platform_data, orient="index", columns=["Platform Info"]
|
||||
)
|
||||
|
||||
raw_results_json = results_to_json(
|
||||
latency_results, throughput_results, serving_results
|
||||
)
|
||||
|
||||
# remapping the key, for visualization purpose
|
||||
if not latency_results.empty:
|
||||
latency_results = latency_results[list(latency_column_mapping.keys())].rename(
|
||||
columns=latency_column_mapping
|
||||
)
|
||||
if not serving_results.empty:
|
||||
valid_columns = [
|
||||
col for col in serving_column_mapping if col in serving_results.columns
|
||||
]
|
||||
serving_results = serving_results[valid_columns].rename(
|
||||
columns=serving_column_mapping
|
||||
)
|
||||
if not throughput_results.empty:
|
||||
throughput_results = throughput_results[
|
||||
list(throughput_results_column_mapping.keys())
|
||||
].rename(columns=throughput_results_column_mapping)
|
||||
|
||||
processed_results_json = results_to_json(
|
||||
latency_results, throughput_results, serving_results
|
||||
)
|
||||
|
||||
for df in [latency_results, serving_results, throughput_results]:
|
||||
if df.empty:
|
||||
continue
|
||||
|
||||
# Sort all dataframes by their respective "Test name" columns
|
||||
df.sort_values(by="Test name", inplace=True)
|
||||
|
||||
# The GPUs sometimes come in format of "GPUTYPE\nGPUTYPE\n...",
|
||||
# we want to turn it into "8xGPUTYPE"
|
||||
df["GPU"] = df["GPU"].apply(
|
||||
lambda x: "{}x{}".format(len(x.split("\n")), x.split("\n")[0])
|
||||
)
|
||||
|
||||
# get markdown tables
|
||||
latency_md_table = tabulate(
|
||||
latency_results, headers="keys", tablefmt="pipe", showindex=False
|
||||
)
|
||||
serving_md_table = tabulate(
|
||||
serving_results, headers="keys", tablefmt="pipe", showindex=False
|
||||
)
|
||||
throughput_md_table = tabulate(
|
||||
throughput_results, headers="keys", tablefmt="pipe", showindex=False
|
||||
)
|
||||
platform_md_table = tabulate(
|
||||
platform_results, headers="keys", tablefmt="pipe", showindex=True
|
||||
)
|
||||
|
||||
# document the result
|
||||
md_file = "benchmark_results.md"
|
||||
json_file = "benchmark_results.json"
|
||||
with open(results_folder / md_file, "w") as f:
|
||||
results = read_markdown(
|
||||
"../.buildkite/performance-benchmarks/"
|
||||
"performance-benchmarks-descriptions.md"
|
||||
)
|
||||
results = results.format(
|
||||
latency_tests_markdown_table=latency_md_table,
|
||||
throughput_tests_markdown_table=throughput_md_table,
|
||||
serving_tests_markdown_table=serving_md_table,
|
||||
platform_markdown_table=platform_md_table,
|
||||
benchmarking_results_in_json_string=processed_results_json,
|
||||
)
|
||||
f.write(results)
|
||||
|
||||
# document benchmarking results in json
|
||||
with open(results_folder / json_file, "w") as f:
|
||||
results = (
|
||||
latency_results.to_dict(orient="records")
|
||||
+ throughput_results.to_dict(orient="records")
|
||||
+ serving_results.to_dict(orient="records")
|
||||
)
|
||||
f.write(json.dumps(results))
|
||||
@@ -1,224 +0,0 @@
|
||||
#!/bin/bash
|
||||
|
||||
# Currently FP8 benchmark is NOT enabled.
|
||||
|
||||
set -x
|
||||
server_params=$1
|
||||
common_params=$2
|
||||
|
||||
json2args() {
|
||||
# transforms the JSON string to command line args, and '_' is replaced to '-'
|
||||
# example:
|
||||
# input: { "model": "meta-llama/Llama-2-7b-chat-hf", "tensor_parallel_size": 1 }
|
||||
# output: --model meta-llama/Llama-2-7b-chat-hf --tensor-parallel-size 1
|
||||
local json_string=$1
|
||||
local args=$(
|
||||
echo "$json_string" | jq -r '
|
||||
to_entries |
|
||||
map("--" + (.key | gsub("_"; "-")) + " " + (.value | tostring)) |
|
||||
join(" ")
|
||||
'
|
||||
)
|
||||
echo "$args"
|
||||
}
|
||||
|
||||
launch_trt_server() {
|
||||
|
||||
model_path=$(echo "$common_params" | jq -r '.model')
|
||||
model_name="${model_path#*/}"
|
||||
model_type=$(echo "$server_params" | jq -r '.model_type')
|
||||
model_dtype=$(echo "$server_params" | jq -r '.model_dtype')
|
||||
model_tp_size=$(echo "$common_params" | jq -r '.tp')
|
||||
max_batch_size=$(echo "$server_params" | jq -r '.max_batch_size')
|
||||
max_input_len=$(echo "$server_params" | jq -r '.max_input_len')
|
||||
max_seq_len=$(echo "$server_params" | jq -r '.max_seq_len')
|
||||
max_num_tokens=$(echo "$server_params" | jq -r '.max_num_tokens')
|
||||
trt_llm_version=$(echo "$server_params" | jq -r '.trt_llm_version')
|
||||
|
||||
# create model caching directory
|
||||
cd ~
|
||||
rm -rf models
|
||||
mkdir -p models
|
||||
cd models
|
||||
models_dir=$(pwd)
|
||||
trt_model_path=${models_dir}/${model_name}-trt-ckpt
|
||||
trt_engine_path=${models_dir}/${model_name}-trt-engine
|
||||
|
||||
# clone tensorrt backend
|
||||
cd /
|
||||
rm -rf tensorrtllm_backend
|
||||
git clone https://github.com/triton-inference-server/tensorrtllm_backend.git
|
||||
git lfs install
|
||||
cd tensorrtllm_backend
|
||||
git checkout "$trt_llm_version"
|
||||
git submodule update --init --recursive
|
||||
|
||||
# build trtllm engine
|
||||
cd /tensorrtllm_backend
|
||||
cd "./tensorrt_llm/examples/${model_type}"
|
||||
python3 convert_checkpoint.py \
|
||||
--model_dir "${model_path}" \
|
||||
--dtype "${model_dtype}" \
|
||||
--tp_size "${model_tp_size}" \
|
||||
--output_dir "${trt_model_path}"
|
||||
trtllm-build \
|
||||
--checkpoint_dir "${trt_model_path}" \
|
||||
--use_fused_mlp \
|
||||
--reduce_fusion disable \
|
||||
--workers 8 \
|
||||
--gpt_attention_plugin "${model_dtype}" \
|
||||
--gemm_plugin "${model_dtype}" \
|
||||
--tp_size "${model_tp_size}" \
|
||||
--max_batch_size "${max_batch_size}" \
|
||||
--max_input_len "${max_input_len}" \
|
||||
--max_seq_len "${max_seq_len}" \
|
||||
--max_num_tokens "${max_num_tokens}" \
|
||||
--output_dir "${trt_engine_path}"
|
||||
|
||||
# handle triton protobuf files and launch triton server
|
||||
cd /tensorrtllm_backend
|
||||
mkdir triton_model_repo
|
||||
cp -r all_models/inflight_batcher_llm/* triton_model_repo/
|
||||
cd triton_model_repo
|
||||
rm -rf ./tensorrt_llm/1/*
|
||||
cp -r "${trt_engine_path}"/* ./tensorrt_llm/1
|
||||
python3 ../tools/fill_template.py -i tensorrt_llm/config.pbtxt triton_backend:tensorrtllm,engine_dir:/tensorrtllm_backend/triton_model_repo/tensorrt_llm/1,decoupled_mode:true,batching_strategy:inflight_fused_batching,batch_scheduler_policy:guaranteed_no_evict,exclude_input_in_output:true,triton_max_batch_size:2048,max_queue_delay_microseconds:0,max_beam_width:1,max_queue_size:2048,enable_kv_cache_reuse:false
|
||||
python3 ../tools/fill_template.py -i preprocessing/config.pbtxt "triton_max_batch_size:2048,tokenizer_dir:$model_path,preprocessing_instance_count:5"
|
||||
python3 ../tools/fill_template.py -i postprocessing/config.pbtxt "triton_max_batch_size:2048,tokenizer_dir:$model_path,postprocessing_instance_count:5,skip_special_tokens:false"
|
||||
python3 ../tools/fill_template.py -i ensemble/config.pbtxt triton_max_batch_size:"$max_batch_size"
|
||||
python3 ../tools/fill_template.py -i tensorrt_llm_bls/config.pbtxt "triton_max_batch_size:$max_batch_size,decoupled_mode:true,accumulate_tokens:False,bls_instance_count:1"
|
||||
cd /tensorrtllm_backend
|
||||
python3 scripts/launch_triton_server.py \
|
||||
--world_size="${model_tp_size}" \
|
||||
--model_repo=/tensorrtllm_backend/triton_model_repo &
|
||||
|
||||
}
|
||||
|
||||
launch_tgi_server() {
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
server_args=$(json2args "$server_params")
|
||||
|
||||
if echo "$common_params" | jq -e 'has("fp8")' >/dev/null; then
|
||||
echo "Key 'fp8' exists in common params."
|
||||
server_command="/tgi-entrypoint.sh \
|
||||
--model-id $model \
|
||||
--num-shard $tp \
|
||||
--port $port \
|
||||
--quantize fp8 \
|
||||
$server_args"
|
||||
else
|
||||
echo "Key 'fp8' does not exist in common params."
|
||||
server_command="/tgi-entrypoint.sh \
|
||||
--model-id $model \
|
||||
--num-shard $tp \
|
||||
--port $port \
|
||||
$server_args"
|
||||
fi
|
||||
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
|
||||
}
|
||||
|
||||
launch_lmdeploy_server() {
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
server_args=$(json2args "$server_params")
|
||||
|
||||
server_command="lmdeploy serve api_server $model \
|
||||
--tp $tp \
|
||||
--server-port $port \
|
||||
$server_args"
|
||||
|
||||
# run the server
|
||||
echo "Server command: $server_command"
|
||||
bash -c "$server_command" &
|
||||
}
|
||||
|
||||
launch_sglang_server() {
|
||||
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
server_args=$(json2args "$server_params")
|
||||
|
||||
if echo "$common_params" | jq -e 'has("fp8")' >/dev/null; then
|
||||
echo "Key 'fp8' exists in common params. Use neuralmagic fp8 model for convenience."
|
||||
model=$(echo "$common_params" | jq -r '.neuralmagic_quantized_model')
|
||||
server_command="python3 \
|
||||
-m sglang.launch_server \
|
||||
--tp $tp \
|
||||
--model-path $model \
|
||||
--port $port \
|
||||
$server_args"
|
||||
else
|
||||
echo "Key 'fp8' does not exist in common params."
|
||||
server_command="python3 \
|
||||
-m sglang.launch_server \
|
||||
--tp $tp \
|
||||
--model-path $model \
|
||||
--port $port \
|
||||
$server_args"
|
||||
fi
|
||||
|
||||
# run the server
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
}
|
||||
|
||||
launch_vllm_server() {
|
||||
|
||||
export VLLM_HOST_IP=$(hostname -I | awk '{print $1}')
|
||||
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
server_args=$(json2args "$server_params")
|
||||
|
||||
if echo "$common_params" | jq -e 'has("fp8")' >/dev/null; then
|
||||
echo "Key 'fp8' exists in common params. Use neuralmagic fp8 model for convenience."
|
||||
model=$(echo "$common_params" | jq -r '.neuralmagic_quantized_model')
|
||||
server_command="vllm serve $model \
|
||||
-tp $tp \
|
||||
--port $port \
|
||||
$server_args"
|
||||
else
|
||||
echo "Key 'fp8' does not exist in common params."
|
||||
server_command="vllm serve $model \
|
||||
-tp $tp \
|
||||
--port $port \
|
||||
$server_args"
|
||||
fi
|
||||
|
||||
# run the server
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
if [[ "$CURRENT_LLM_SERVING_ENGINE" == "trt" ]]; then
|
||||
launch_trt_server
|
||||
fi
|
||||
|
||||
if [[ "$CURRENT_LLM_SERVING_ENGINE" == "tgi" ]]; then
|
||||
launch_tgi_server
|
||||
fi
|
||||
|
||||
if [[ "$CURRENT_LLM_SERVING_ENGINE" == "lmdeploy" ]]; then
|
||||
launch_lmdeploy_server
|
||||
fi
|
||||
|
||||
if [[ "$CURRENT_LLM_SERVING_ENGINE" == "sglang" ]]; then
|
||||
launch_sglang_server
|
||||
fi
|
||||
|
||||
if [[ "$CURRENT_LLM_SERVING_ENGINE" == *"vllm"* ]]; then
|
||||
launch_vllm_server
|
||||
fi
|
||||
}
|
||||
|
||||
main
|
||||
@@ -1,896 +0,0 @@
|
||||
#!/bin/bash
|
||||
# This script assumes that we are already inside the vllm/ directory
|
||||
# Benchmarking results will be available inside vllm/benchmarks/results/
|
||||
|
||||
# Do not set -e, as the mixtral 8x22B model tends to crash occasionally
|
||||
# and we still want to see other benchmarking results even when mixtral crashes.
|
||||
set -x
|
||||
set -o pipefail
|
||||
|
||||
# Environment-driven debug controls (like ON_CPU=1)
|
||||
DRY_RUN="${DRY_RUN:-0}"
|
||||
MODEL_FILTER="${MODEL_FILTER:-}"
|
||||
DTYPE_FILTER="${DTYPE_FILTER:-}"
|
||||
|
||||
# Adaptive search controls
|
||||
ENABLE_ADAPTIVE_CONCURRENCY="${ENABLE_ADAPTIVE_CONCURRENCY:-0}"
|
||||
SLA_TTFT_MS="${SLA_TTFT_MS:-3000}"
|
||||
SLA_TPOT_MS="${SLA_TPOT_MS:-100}"
|
||||
ADAPTIVE_MAX_PROBES="${ADAPTIVE_MAX_PROBES:-8}"
|
||||
ADAPTIVE_MAX_CONCURRENCY="${ADAPTIVE_MAX_CONCURRENCY:-1024}"
|
||||
|
||||
check_gpus() {
|
||||
if command -v nvidia-smi; then
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | grep -c . || true)
|
||||
elif command -v amd-smi; then
|
||||
declare -g gpu_count=$(amd-smi list | grep -c 'GPU' || true)
|
||||
elif command -v hl-smi; then
|
||||
declare -g gpu_count=$(hl-smi --list | grep -ci "Module ID" || true)
|
||||
fi
|
||||
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
declare -g arch_suffix=''
|
||||
|
||||
if command -v nvidia-smi; then
|
||||
declare -g gpu_type=$(nvidia-smi --query-gpu=name --format=csv,noheader | awk '{print $2}')
|
||||
elif command -v amd-smi; then
|
||||
declare -g gpu_type=$(amd-smi static -g 0 -a | grep 'MARKET_NAME' | awk '{print $2}')
|
||||
elif command -v hl-smi; then
|
||||
declare -g gpu_type=$(hl-smi -q | grep "Product Name" | head -n 1 | awk -F ':' '{print $2}' | sed 's/^ *//')
|
||||
arch_suffix='-hpu'
|
||||
fi
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
check_cpus() {
|
||||
# check the number of CPUs and NUMA Node and GPU type.
|
||||
declare -g numa_count=$(lscpu | grep "NUMA node(s):" | awk '{print $3}')
|
||||
if [[ $numa_count -gt 0 ]]; then
|
||||
echo "NUMA found."
|
||||
echo "$numa_count"
|
||||
else
|
||||
echo "Need at least 1 NUMA to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
if [[ "$(uname -m)" == "aarch64" ]] || [[ "$(uname -m)" == "arm64" ]]; then
|
||||
declare -g gpu_type="arm64-cpu"
|
||||
else
|
||||
declare -g gpu_type="cpu"
|
||||
fi
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
check_hf_token() {
|
||||
# check if HF_TOKEN is available and valid
|
||||
if [[ -z "$HF_TOKEN" ]]; then
|
||||
echo "Error: HF_TOKEN is not set."
|
||||
exit 1
|
||||
elif [[ ! "$HF_TOKEN" =~ ^hf_ ]]; then
|
||||
echo "Error: HF_TOKEN does not start with 'hf_'."
|
||||
exit 1
|
||||
else
|
||||
echo "HF_TOKEN is set and valid."
|
||||
fi
|
||||
}
|
||||
|
||||
ensure_sharegpt_downloaded() {
|
||||
local FILE=ShareGPT_V3_unfiltered_cleaned_split.json
|
||||
if [ ! -f "$FILE" ]; then
|
||||
wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/$FILE
|
||||
else
|
||||
echo "$FILE already exists."
|
||||
fi
|
||||
}
|
||||
|
||||
json2args() {
|
||||
# transforms the JSON string to command line args, and '_' is replaced to '-'
|
||||
# example:
|
||||
# input: { "model": "meta-llama/Llama-2-7b-chat-hf", "tensor_parallel_size": 1 }
|
||||
# output: --model meta-llama/Llama-2-7b-chat-hf --tensor-parallel-size 1
|
||||
local json_string=$1
|
||||
local args=$(
|
||||
echo "$json_string" | jq -r '
|
||||
to_entries |
|
||||
map("--" + (.key | gsub("_"; "-")) + " " + (.value | tostring)) |
|
||||
join(" ")
|
||||
'
|
||||
)
|
||||
echo "$args"
|
||||
}
|
||||
|
||||
json2envs() {
|
||||
# transforms the JSON string to environment variables.
|
||||
# example:
|
||||
# input: { "VLLM_CPU_KVCACHE_SPACE": 5 }
|
||||
# output: VLLM_CPU_KVCACHE_SPACE=5
|
||||
local json_string=$1
|
||||
local args=$(
|
||||
echo "$json_string" | jq -r '
|
||||
to_entries |
|
||||
map((.key ) + "=" + (.value | tostring)) |
|
||||
join(" ")
|
||||
'
|
||||
)
|
||||
echo "$args"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
local timeout_val="1200"
|
||||
timeout "$timeout_val" bash -c '
|
||||
until curl -sf http://localhost:8000/v1/models >/dev/null; do
|
||||
sleep 1
|
||||
done
|
||||
'
|
||||
}
|
||||
|
||||
kill_processes_launched_by_current_bash() {
|
||||
# Kill all python processes launched from current bash script
|
||||
current_shell_pid=$$
|
||||
processes=$(ps -eo pid,ppid,command | awk -v ppid="$current_shell_pid" -v proc="$1" '$2 == ppid && $3 ~ proc {print $1}')
|
||||
if [ -n "$processes" ]; then
|
||||
echo "Killing the following processes matching '$1':"
|
||||
echo "$processes"
|
||||
echo "$processes" | xargs kill -9
|
||||
else
|
||||
echo "No processes found matching '$1'."
|
||||
fi
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
|
||||
ps -aux
|
||||
lsof -t -i:8000 | xargs -r kill -9
|
||||
pgrep python3 | xargs -r kill -9
|
||||
# vLLM now names the process with VLLM prefix after https://github.com/vllm-project/vllm/pull/21445
|
||||
pgrep VLLM | xargs -r kill -9
|
||||
|
||||
# wait until GPU memory usage smaller than 1GB
|
||||
if command -v nvidia-smi; then
|
||||
while [ "$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits | head -n 1)" -ge 1000 ]; do
|
||||
sleep 1
|
||||
done
|
||||
elif command -v amd-smi; then
|
||||
while [ "$(amd-smi metric -g 0 | grep 'USED_VRAM' | awk '{print $2}')" -ge 1000 ]; do
|
||||
sleep 1
|
||||
done
|
||||
elif command -v hl-smi; then
|
||||
while [ "$(hl-smi -q | grep "Used" | head -n 1 | awk '{print $3}')" -ge 1000 ]; do
|
||||
sleep 1
|
||||
done
|
||||
fi
|
||||
|
||||
# remove vllm config file
|
||||
rm -rf ~/.config/vllm
|
||||
|
||||
}
|
||||
|
||||
upload_to_buildkite() {
|
||||
# upload the benchmarking results to buildkite
|
||||
|
||||
# if the agent binary is not found, skip uploading the results, exit 0
|
||||
# Check if buildkite-agent is available in the PATH or at /workspace/buildkite-agent
|
||||
if command -v buildkite-agent >/dev/null 2>&1; then
|
||||
BUILDKITE_AGENT_COMMAND="buildkite-agent"
|
||||
elif [ -f /workspace/buildkite-agent ]; then
|
||||
BUILDKITE_AGENT_COMMAND="/workspace/buildkite-agent"
|
||||
else
|
||||
echo "buildkite-agent binary not found. Skip uploading the results."
|
||||
return 0
|
||||
fi
|
||||
|
||||
# Use the determined command to annotate and upload artifacts
|
||||
$BUILDKITE_AGENT_COMMAND annotate --style "info" --context "$BUILDKITE_LABEL-benchmark-results" < "$RESULTS_FOLDER/benchmark_results.md"
|
||||
$BUILDKITE_AGENT_COMMAND artifact upload "$RESULTS_FOLDER/*"
|
||||
}
|
||||
|
||||
# -------------------------------
|
||||
# Adaptive concurrency helpers
|
||||
# -------------------------------
|
||||
result_json_path_for_serving() {
|
||||
local test_name=$1
|
||||
local qps=$2
|
||||
local max_concurrency=$3
|
||||
echo "$RESULTS_FOLDER/${test_name}_qps_${qps}_concurrency_${max_concurrency}.json"
|
||||
}
|
||||
|
||||
extract_metric_ms() {
|
||||
local metric_name=$1
|
||||
local json_file=$2
|
||||
|
||||
[[ -f "$json_file" ]] || return 0
|
||||
|
||||
if [[ "$metric_name" == "ttft" ]]; then
|
||||
jq -r '
|
||||
[
|
||||
.ttft_ms.p99?,
|
||||
.metrics.ttft_ms.p99?,
|
||||
.ttft.p99?,
|
||||
.metrics.ttft.p99?,
|
||||
.p99_ttft_ms?,
|
||||
.ttft_ms.mean?,
|
||||
.metrics.ttft_ms.mean?,
|
||||
.ttft.mean?,
|
||||
.metrics.ttft.mean?,
|
||||
.mean_ttft_ms?
|
||||
] | map(select(. != null)) | .[0] // empty
|
||||
' "$json_file"
|
||||
else
|
||||
jq -r '
|
||||
[
|
||||
.tpot_ms.p99?,
|
||||
.metrics.tpot_ms.p99?,
|
||||
.tpot.p99?,
|
||||
.metrics.tpot.p99?,
|
||||
.p99_tpot_ms?,
|
||||
.itl_ms.p99?,
|
||||
.metrics.itl_ms.p99?,
|
||||
.inter_token_latency_ms.p99?,
|
||||
.tpot_ms.mean?,
|
||||
.metrics.tpot_ms.mean?,
|
||||
.tpot.mean?,
|
||||
.metrics.tpot.mean?,
|
||||
.itl_ms.mean?,
|
||||
.metrics.itl_ms.mean?,
|
||||
.mean_tpot_ms?,
|
||||
.mean_itl_ms?
|
||||
] | map(select(. != null)) | .[0] // empty
|
||||
' "$json_file"
|
||||
fi
|
||||
}
|
||||
|
||||
evaluate_sla_from_json() {
|
||||
local json_file=$1
|
||||
local ttft
|
||||
local tpot
|
||||
local pass
|
||||
|
||||
[[ -f "$json_file" ]] || return 2
|
||||
|
||||
ttft=$(extract_metric_ms ttft "$json_file")
|
||||
tpot=$(extract_metric_ms tpot "$json_file")
|
||||
|
||||
[[ -n "$ttft" && -n "$tpot" ]] || return 2
|
||||
|
||||
pass=$(jq -n \
|
||||
--argjson ttft "$ttft" \
|
||||
--argjson tpot "$tpot" \
|
||||
--argjson sla_ttft "$SLA_TTFT_MS" \
|
||||
--argjson sla_tpot "$SLA_TPOT_MS" \
|
||||
'($ttft <= $sla_ttft) and ($tpot <= $sla_tpot)')
|
||||
|
||||
[[ "$pass" == "true" ]]
|
||||
}
|
||||
|
||||
write_adaptive_summary_json() {
|
||||
local summary_file=$1
|
||||
local test_name=$2
|
||||
local qps=$3
|
||||
local static_last_pass=$4
|
||||
local static_first_fail=$5
|
||||
local final_last_pass=$6
|
||||
local final_first_fail=$7
|
||||
|
||||
jq -n \
|
||||
--arg test_name "$test_name" \
|
||||
--arg qps "$qps" \
|
||||
--argjson sla_ttft "$SLA_TTFT_MS" \
|
||||
--argjson sla_tpot "$SLA_TPOT_MS" \
|
||||
--arg static_last_pass "${static_last_pass:-}" \
|
||||
--arg static_first_fail "${static_first_fail:-}" \
|
||||
--arg final_last_pass "${final_last_pass:-}" \
|
||||
--arg final_first_fail "${final_first_fail:-}" \
|
||||
'{
|
||||
test_name: $test_name,
|
||||
qps: $qps,
|
||||
sla_ttft_ms: $sla_ttft,
|
||||
sla_tpot_ms: $sla_tpot,
|
||||
static_last_pass: (if $static_last_pass == "" then null else ($static_last_pass | tonumber) end),
|
||||
static_first_fail: (if $static_first_fail == "" then null else ($static_first_fail | tonumber) end),
|
||||
final_last_pass: (if $final_last_pass == "" then null else ($final_last_pass | tonumber) end),
|
||||
final_first_fail: (if $final_first_fail == "" then null else ($final_first_fail | tonumber) end)
|
||||
}' > "$summary_file"
|
||||
}
|
||||
|
||||
run_single_serving_probe() {
|
||||
local test_name=$1
|
||||
local qps=$2
|
||||
local max_concurrency=$3
|
||||
local tp=$4
|
||||
local compilation_config_mode=$5
|
||||
local optimization_level=$6
|
||||
local client_args_effective=$7
|
||||
local client_remote_args=$8
|
||||
local server_command=$9
|
||||
|
||||
local new_test_name="${test_name}_qps_${qps}_concurrency_${max_concurrency}"
|
||||
local result_json
|
||||
local num_prompts_arg=""
|
||||
local client_command
|
||||
|
||||
result_json=$(result_json_path_for_serving "$test_name" "$qps" "$max_concurrency")
|
||||
|
||||
if [[ -f "$result_json" ]]; then
|
||||
evaluate_sla_from_json "$result_json"
|
||||
return $?
|
||||
fi
|
||||
|
||||
if [[ -n "${PROMPTS_PER_CONCURRENCY}" ]]; then
|
||||
num_prompts=$(( max_concurrency * PROMPTS_PER_CONCURRENCY ))
|
||||
if (( num_prompts < MIN_NUM_PROMPTS )); then num_prompts=$MIN_NUM_PROMPTS; fi
|
||||
if (( num_prompts > MAX_NUM_PROMPTS )); then num_prompts=$MAX_NUM_PROMPTS; fi
|
||||
num_prompts_arg="--num-prompts $num_prompts"
|
||||
fi
|
||||
|
||||
client_command="vllm bench serve \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
--max-concurrency $max_concurrency \
|
||||
$num_prompts_arg \
|
||||
--metadata tensor_parallel_size=$tp compilation_config.mode=$compilation_config_mode optimization_level=$optimization_level adaptive_search=1 \
|
||||
$client_args_effective $client_remote_args "
|
||||
|
||||
echo "Adaptive probe: $client_command"
|
||||
|
||||
if [[ "${DRY_RUN:-0}" != "1" ]]; then
|
||||
bash -c "$client_command"
|
||||
fi
|
||||
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu,
|
||||
adaptive_search: true
|
||||
}')
|
||||
echo "$jq_output" > "$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
evaluate_sla_from_json "$result_json"
|
||||
}
|
||||
|
||||
adaptive_refine_from_static_results() {
|
||||
local test_name=$1
|
||||
local qps=$2
|
||||
local max_concurrency_list_raw=$3
|
||||
local tp=$4
|
||||
local compilation_config_mode=$5
|
||||
local optimization_level=$6
|
||||
local client_args_effective=$7
|
||||
local client_remote_args=$8
|
||||
local server_command=$9
|
||||
|
||||
local sorted_points
|
||||
local point
|
||||
local rc
|
||||
local static_last_pass=""
|
||||
local static_first_fail=""
|
||||
local largest_static=""
|
||||
local step_hint=1
|
||||
local previous_point=""
|
||||
local low
|
||||
local high
|
||||
local mid
|
||||
local probes=0
|
||||
local summary_file="$RESULTS_FOLDER/${test_name}_qps_${qps}_sla_summary.json"
|
||||
|
||||
[[ "${ENABLE_ADAPTIVE_CONCURRENCY}" == "1" ]] || return 0
|
||||
[[ "${DRY_RUN:-0}" != "1" ]] || return 0
|
||||
|
||||
sorted_points=$(for point in $max_concurrency_list_raw; do printf '%s\n' "$point"; done | tr -d "'" | awk '/^[0-9]+$/' | sort -n | uniq)
|
||||
[[ -n "$sorted_points" ]] || return 0
|
||||
|
||||
while read -r point; do
|
||||
[[ -z "$point" ]] && continue
|
||||
largest_static="$point"
|
||||
evaluate_sla_from_json "$(result_json_path_for_serving "$test_name" "$qps" "$point")"
|
||||
rc=$?
|
||||
if (( rc == 0 )); then
|
||||
static_last_pass="$point"
|
||||
elif (( rc == 1 )); then
|
||||
if [[ -n "$static_last_pass" ]]; then
|
||||
static_first_fail="$point"
|
||||
break
|
||||
fi
|
||||
fi
|
||||
|
||||
if [[ -n "$previous_point" ]]; then
|
||||
step_hint=$(( point - previous_point ))
|
||||
if (( step_hint < 1 )); then step_hint=1; fi
|
||||
fi
|
||||
previous_point="$point"
|
||||
done <<< "$sorted_points"
|
||||
|
||||
if [[ -z "$static_last_pass" ]]; then
|
||||
write_adaptive_summary_json "$summary_file" "$test_name" "$qps" "" "$static_first_fail" "" "$static_first_fail"
|
||||
return 0
|
||||
fi
|
||||
|
||||
if [[ -n "$static_first_fail" ]]; then
|
||||
low=$static_last_pass
|
||||
high=$static_first_fail
|
||||
while (( low + 1 < high )) && (( probes < ADAPTIVE_MAX_PROBES )); do
|
||||
mid=$(( (low + high) / 2 ))
|
||||
probes=$(( probes + 1 ))
|
||||
run_single_serving_probe \
|
||||
"$test_name" "$qps" "$mid" "$tp" \
|
||||
"$compilation_config_mode" "$optimization_level" \
|
||||
"$client_args_effective" "$client_remote_args" "$server_command"
|
||||
rc=$?
|
||||
if (( rc == 0 )); then
|
||||
low=$mid
|
||||
elif (( rc == 1 )); then
|
||||
high=$mid
|
||||
else
|
||||
break
|
||||
fi
|
||||
done
|
||||
write_adaptive_summary_json "$summary_file" "$test_name" "$qps" "$static_last_pass" "$static_first_fail" "$low" "$high"
|
||||
return 0
|
||||
fi
|
||||
|
||||
low=$largest_static
|
||||
high=""
|
||||
while (( probes < ADAPTIVE_MAX_PROBES )); do
|
||||
point=$(( low + step_hint ))
|
||||
if (( point > ADAPTIVE_MAX_CONCURRENCY )); then
|
||||
point=$ADAPTIVE_MAX_CONCURRENCY
|
||||
fi
|
||||
(( point > low )) || break
|
||||
probes=$(( probes + 1 ))
|
||||
run_single_serving_probe \
|
||||
"$test_name" "$qps" "$point" "$tp" \
|
||||
"$compilation_config_mode" "$optimization_level" \
|
||||
"$client_args_effective" "$client_remote_args" "$server_command"
|
||||
rc=$?
|
||||
if (( rc == 0 )); then
|
||||
low=$point
|
||||
(( point == ADAPTIVE_MAX_CONCURRENCY )) && break
|
||||
step_hint=$(( step_hint * 2 ))
|
||||
if (( step_hint < 1 )); then step_hint=1; fi
|
||||
elif (( rc == 1 )); then
|
||||
high=$point
|
||||
break
|
||||
else
|
||||
break
|
||||
fi
|
||||
done
|
||||
|
||||
if [[ -n "$high" ]]; then
|
||||
while (( low + 1 < high )) && (( probes < ADAPTIVE_MAX_PROBES )); do
|
||||
mid=$(( (low + high) / 2 ))
|
||||
probes=$(( probes + 1 ))
|
||||
run_single_serving_probe \
|
||||
"$test_name" "$qps" "$mid" "$tp" \
|
||||
"$compilation_config_mode" "$optimization_level" \
|
||||
"$client_args_effective" "$client_remote_args" "$server_command"
|
||||
rc=$?
|
||||
if (( rc == 0 )); then
|
||||
low=$mid
|
||||
elif (( rc == 1 )); then
|
||||
high=$mid
|
||||
else
|
||||
break
|
||||
fi
|
||||
done
|
||||
fi
|
||||
|
||||
write_adaptive_summary_json "$summary_file" "$test_name" "$qps" "$static_last_pass" "" "$low" "$high"
|
||||
}
|
||||
|
||||
run_benchmark_tests() {
|
||||
# run benchmark tests using `vllm bench <test_type>` command
|
||||
# $1: test type (latency or throughput)
|
||||
# $2: a json file specifying test cases
|
||||
|
||||
local test_type=$1
|
||||
local test_file=$2
|
||||
|
||||
# Iterate over tests
|
||||
jq -c '.[]' "$test_file" | while read -r params; do
|
||||
# get the test name, and append the GPU type back to it.
|
||||
test_name=$(echo "$params" | jq -r '.test_name')
|
||||
if [[ ! "$test_name" =~ ^${test_type}_ ]]; then
|
||||
echo "In ${test_type}-test.json, test_name must start with \"${test_type}_\"."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# get arguments
|
||||
bench_params=$(echo "$params" | jq -r '.parameters')
|
||||
bench_args=$(json2args "$bench_params")
|
||||
bench_environment_variables=$(echo "$params" | jq -r '.environment_variables')
|
||||
bench_envs=$(json2envs "$bench_environment_variables")
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
tp=$(echo "$bench_params" | jq -r '.tensor_parallel_size')
|
||||
if [[ "$ON_CPU" == "1" ]]; then
|
||||
pp=$(echo "$bench_params" | jq -r '.pipeline_parallel_size // 1')
|
||||
world_size=$(($tp*$pp))
|
||||
if [[ $numa_count -lt $world_size && -z "${REMOTE_HOST}" ]]; then
|
||||
echo "Required world-size $world_size but only $numa_count NUMA nodes found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
else
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
fi
|
||||
|
||||
bench_command=" $bench_envs vllm bench $test_type \
|
||||
--output-json $RESULTS_FOLDER/${test_name}.json \
|
||||
$bench_args"
|
||||
|
||||
echo "Running test case $test_name"
|
||||
echo "${test_type^} command: $bench_command"
|
||||
|
||||
# recording benchmarking command and GPU command
|
||||
jq_output=$(jq -n \
|
||||
--arg command "$bench_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
--arg test_type "$test_type" \
|
||||
'{
|
||||
($test_type + "_command"): $command,
|
||||
gpu_type: $gpu
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/$test_name.commands"
|
||||
|
||||
# run the benchmark
|
||||
eval "$bench_command"
|
||||
|
||||
kill_gpu_processes
|
||||
|
||||
done
|
||||
}
|
||||
|
||||
run_latency_tests() { run_benchmark_tests "latency" "$1"; }
|
||||
run_startup_tests() { run_benchmark_tests "startup" "$1"; }
|
||||
run_throughput_tests() { run_benchmark_tests "throughput" "$1"; }
|
||||
|
||||
merge_serving_tests_stream() {
|
||||
# Emit merged serving test objects, optionally filtered by MODEL_FILTER/DTYPE_FILTER in DRY_RUN mode.
|
||||
# This helper does NOT modify JSON; it only filters the stream in dry-run mode.
|
||||
local serving_test_file="$1"
|
||||
# shellcheck disable=SC2016
|
||||
local merged='
|
||||
if type == "array" then
|
||||
# Plain format: test cases array
|
||||
.[]
|
||||
elif (type == "object" and has("tests")) then
|
||||
# merge the default parameters into each test cases
|
||||
. as $root
|
||||
| ($root.defaults // {}) as $d
|
||||
| ($root.tests // [])[]
|
||||
# default qps / max_concurrency from defaults if missing
|
||||
| .qps_list = (.qps_list // $d.qps_list)
|
||||
| .max_concurrency_list = (.max_concurrency_list // $d.max_concurrency_list)
|
||||
# merge envs / params: test overrides defaults
|
||||
| .server_environment_variables =
|
||||
(($d.server_environment_variables // {}) + (.server_environment_variables // {}))
|
||||
| .server_parameters =
|
||||
(($d.server_parameters // {}) + (.server_parameters // {}))
|
||||
| .client_parameters =
|
||||
(($d.client_parameters // {}) + (.client_parameters // {}))
|
||||
else
|
||||
error("Unsupported serving test file format: must be array or object with .tests")
|
||||
end
|
||||
'
|
||||
|
||||
jq -c "$merged" "$serving_test_file" | \
|
||||
if [[ "${DRY_RUN:-0}" == "1" && ( "${MODEL_FILTER}${DTYPE_FILTER}" != "" ) ]]; then
|
||||
jq -c --arg model "$MODEL_FILTER" --arg dtype "$DTYPE_FILTER" '
|
||||
select((($model|length)==0)
|
||||
or ((.server_parameters.model // "") == $model)
|
||||
or ((.client_parameters.model // "") == $model))
|
||||
| select((($dtype|length)==0) or ((.server_parameters.dtype // "") == $dtype))
|
||||
'
|
||||
else
|
||||
cat
|
||||
fi
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `vllm bench serve` command
|
||||
# $1: a json file specifying serving test cases
|
||||
#
|
||||
# Supported JSON formats:
|
||||
# 1) Plain format: top-level array
|
||||
# [ { "test_name": "...", "server_parameters": {...}, ... }, ... ]
|
||||
#
|
||||
# 2) Default parameters field + plain format tests
|
||||
# {
|
||||
# "defaults": { ... },
|
||||
# "tests": [ { "test_name": "...", "server_parameters": {...}, ... }, ... ]
|
||||
# }
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# In dry-run mode, if filters are provided but no tests match, fail fast.
|
||||
if [[ "${DRY_RUN:-0}" == "1" && ( "${MODEL_FILTER}${DTYPE_FILTER}" != "" ) ]]; then
|
||||
local count
|
||||
count=$(merge_serving_tests_stream "$serving_test_file" | wc -l | tr -d ' ')
|
||||
if [[ "$count" -eq 0 ]]; then
|
||||
echo "No matching serving tests found in $serving_test_file for model='$MODEL_FILTER' dtype='$DTYPE_FILTER'." >&2
|
||||
return 0
|
||||
fi
|
||||
fi
|
||||
|
||||
# Iterate over serving tests (merged + optional filtered stream)
|
||||
merge_serving_tests_stream "$serving_test_file" | while read -r params; do
|
||||
# get the test name, and append the GPU type back to it.
|
||||
test_name=$(echo "$params" | jq -r '.test_name')
|
||||
if [[ ! "$test_name" =~ ^serving_ ]]; then
|
||||
echo "In serving-test.json, test_name must start with \"serving_\"."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# get client and server arguments (after merged the default parameters)
|
||||
server_params=$(echo "$params" | jq -r '.server_parameters')
|
||||
server_envs=$(echo "$params" | jq -r '.server_environment_variables')
|
||||
client_params=$(echo "$params" | jq -r '.client_parameters')
|
||||
|
||||
# vLLM serve CLI: model must be positional (no --model). Convert server_parameters accordingly.
|
||||
server_model=$(echo "$server_params" | jq -r '.model // empty')
|
||||
if [[ -z "$server_model" || "$server_model" == "null" ]]; then
|
||||
echo "Error: serving test '$test_name' is missing server_parameters.model" >&2
|
||||
exit 1
|
||||
fi
|
||||
server_params_no_model=$(echo "$server_params" | jq -c 'del(.model)')
|
||||
server_args=$(json2args "$server_params_no_model")
|
||||
|
||||
server_envs=$(json2envs "$server_envs")
|
||||
client_args=$(json2args "$client_params")
|
||||
|
||||
# ------------------------------------------------------------
|
||||
# Option 1: Dynamic num-prompts scaling based on max_concurrency
|
||||
#
|
||||
# If PROMPTS_PER_CONCURRENCY is set, override JSON num_prompts with:
|
||||
# num_prompts = max_concurrency * PROMPTS_PER_CONCURRENCY
|
||||
#
|
||||
# If PROMPTS_PER_CONCURRENCY is NOT set, keep JSON num_prompts behavior
|
||||
# unchanged (i.e., whatever is in serving-tests-*.json).
|
||||
# ------------------------------------------------------------
|
||||
PROMPTS_PER_CONCURRENCY="${PROMPTS_PER_CONCURRENCY-}" # no default on purpose
|
||||
MIN_NUM_PROMPTS="${MIN_NUM_PROMPTS:-1}"
|
||||
MAX_NUM_PROMPTS="${MAX_NUM_PROMPTS:-1000000}"
|
||||
|
||||
if [[ -n "${PROMPTS_PER_CONCURRENCY}" ]]; then
|
||||
# Remove any fixed --num-prompts from JSON-derived args (avoid duplicates)
|
||||
# Remove any fixed --num-prompts from JSON-derived args (avoid duplicates)
|
||||
# Handles: --num-prompts 123 and --num-prompts=123
|
||||
client_args_no_np="$(
|
||||
printf ' %s ' "$client_args" \
|
||||
| sed -E \
|
||||
-e 's/[[:space:]]--num-prompts=([^[:space:]]+)([[:space:]]|$)/ /g' \
|
||||
-e 's/[[:space:]]--num-prompts[[:space:]]+([^[:space:]]+)([[:space:]]|$)/ /g'
|
||||
)"
|
||||
# normalize whitespace
|
||||
client_args_no_np="$(echo "$client_args_no_np" | tr -s ' ' | sed -E 's/^ //; s/ $//')"
|
||||
client_args_no_np="$(echo "$client_args_no_np" | xargs)"
|
||||
client_args_effective="$client_args_no_np"
|
||||
else
|
||||
client_args_effective="$client_args"
|
||||
fi
|
||||
# qps_list
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# max_concurrency_list (fallback to num_prompts if missing)
|
||||
max_concurrency_list=$(echo "$params" | jq -r '.max_concurrency_list')
|
||||
if [[ -z "$max_concurrency_list" || "$max_concurrency_list" == "null" ]]; then
|
||||
num_prompts=$(echo "$client_params" | jq -r '.num_prompts')
|
||||
max_concurrency_list="[$num_prompts]"
|
||||
fi
|
||||
max_concurrency_list=$(echo "$max_concurrency_list" | jq -r '.[] | @sh')
|
||||
echo "Running over max concurrency list $max_concurrency_list"
|
||||
|
||||
# check if there is enough resources to run the test
|
||||
tp=$(echo "$server_params" | jq -r '.tensor_parallel_size')
|
||||
if [[ "$ON_CPU" == "1" ]]; then
|
||||
pp=$(echo "$server_params" | jq -r '.pipeline_parallel_size // 1')
|
||||
world_size=$(($tp*$pp))
|
||||
if [[ $numa_count -lt $world_size && -z "${REMOTE_HOST}" ]]; then
|
||||
echo "Required world-size $world_size but only $numa_count NUMA nodes found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
else
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
fi
|
||||
|
||||
# check if server model and client model is aligned
|
||||
client_model=$(echo "$client_params" | jq -r '.model')
|
||||
if [[ $server_model != "$client_model" ]]; then
|
||||
echo "Server model and client model must be the same. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
server_command="$server_envs vllm serve $server_model \
|
||||
$server_args"
|
||||
|
||||
# run the server
|
||||
echo "Running test case $test_name"
|
||||
echo "Server command: $server_command"
|
||||
# support remote vllm server
|
||||
client_remote_args=""
|
||||
if [[ -z "${REMOTE_HOST}" && "${DRY_RUN:-0}" != "1" ]]; then
|
||||
bash -c "$server_command" &
|
||||
server_pid=$!
|
||||
# wait until the server is alive
|
||||
if wait_for_server; then
|
||||
echo ""
|
||||
echo "vLLM server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "vLLM failed to start within the timeout period."
|
||||
fi
|
||||
elif [[ "${DRY_RUN:-0}" == "1" ]]; then
|
||||
# dry-run: don't start server
|
||||
echo "Dry Run."
|
||||
else
|
||||
server_command="Using Remote Server $REMOTE_HOST $REMOTE_PORT"
|
||||
if [[ ${REMOTE_PORT} ]]; then
|
||||
client_remote_args=" --host=$REMOTE_HOST --port=$REMOTE_PORT "
|
||||
else
|
||||
client_remote_args=" --host=$REMOTE_HOST "
|
||||
fi
|
||||
fi
|
||||
|
||||
# save the compilation mode and optimization level on the serving results
|
||||
# whenever they are set
|
||||
compilation_config_mode=$(echo "$server_params" | jq -r '."compilation_config.mode" // empty')
|
||||
optimization_level=$(echo "$server_params" | jq -r '.optimization_level // empty')
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
qps="inf"
|
||||
fi
|
||||
|
||||
# iterate over different max_concurrency
|
||||
for max_concurrency in $max_concurrency_list; do
|
||||
new_test_name="${test_name}_qps_${qps}_concurrency_${max_concurrency}"
|
||||
echo " new test name $new_test_name"
|
||||
# If PROMPTS_PER_CONCURRENCY is set, compute per-concurrency --num-prompts.
|
||||
num_prompts_arg=""
|
||||
if [[ -n "${PROMPTS_PER_CONCURRENCY}" ]]; then
|
||||
num_prompts=$(( max_concurrency * PROMPTS_PER_CONCURRENCY ))
|
||||
if (( num_prompts < MIN_NUM_PROMPTS )); then num_prompts=$MIN_NUM_PROMPTS; fi
|
||||
if (( num_prompts > MAX_NUM_PROMPTS )); then num_prompts=$MAX_NUM_PROMPTS; fi
|
||||
num_prompts_arg="--num-prompts $num_prompts"
|
||||
fi
|
||||
# pass the tensor parallel size, the compilation mode, and the optimization
|
||||
# level to the client so that they can be used on the benchmark dashboard
|
||||
client_command="vllm bench serve \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
--max-concurrency $max_concurrency \
|
||||
$num_prompts_arg \
|
||||
--metadata tensor_parallel_size=$tp compilation_config.mode=$compilation_config_mode optimization_level=$optimization_level \
|
||||
$client_args_effective $client_remote_args "
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
if [[ "${DRY_RUN:-0}" != "1" ]]; then
|
||||
bash -c "$client_command"
|
||||
fi
|
||||
|
||||
# record the benchmarking commands
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
done
|
||||
|
||||
adaptive_refine_from_static_results \
|
||||
"$test_name" "$qps" "$max_concurrency_list" "$tp" \
|
||||
"$compilation_config_mode" "$optimization_level" \
|
||||
"$client_args_effective" "$client_remote_args" "$server_command"
|
||||
done
|
||||
|
||||
# clean up
|
||||
if [[ "${DRY_RUN:-0}" != "1" ]]; then
|
||||
kill -9 "$server_pid"
|
||||
kill_gpu_processes
|
||||
fi
|
||||
done
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
local ARCH
|
||||
ARCH=''
|
||||
if [[ "$ON_CPU" == "1" ]]; then
|
||||
check_cpus
|
||||
ARCH="-$gpu_type"
|
||||
else
|
||||
check_gpus
|
||||
ARCH="$arch_suffix"
|
||||
fi
|
||||
|
||||
# DRY_RUN does not execute vLLM; do not require HF_TOKEN.
|
||||
if [[ "${DRY_RUN:-0}" != "1" ]]; then
|
||||
check_hf_token
|
||||
else
|
||||
echo "DRY_RUN=1 -> skip HF_TOKEN validation"
|
||||
fi
|
||||
|
||||
# dependencies
|
||||
(which wget && which curl) || (apt-get update && apt-get install -y wget curl)
|
||||
(which jq) || (apt-get update && apt-get -y install jq)
|
||||
(which lsof) || (apt-get update && apt-get install -y lsof)
|
||||
|
||||
# get the current IP address, required by `vllm bench serve` command
|
||||
export VLLM_HOST_IP=$(hostname -I | awk '{print $1}')
|
||||
# turn of the reporting of the status of each request, to clean up the terminal output
|
||||
export VLLM_LOGGING_LEVEL="WARNING"
|
||||
|
||||
# prepare for benchmarking
|
||||
cd benchmarks || exit 1
|
||||
ensure_sharegpt_downloaded
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
QUICK_BENCHMARK_ROOT=../.buildkite/performance-benchmarks/
|
||||
|
||||
# dump vllm info via vllm collect-env
|
||||
env_output=$(vllm collect-env)
|
||||
echo "$env_output" >"$RESULTS_FOLDER/vllm_env.txt"
|
||||
|
||||
# benchmarking
|
||||
run_serving_tests $QUICK_BENCHMARK_ROOT/tests/"${SERVING_JSON:-serving-tests$ARCH.json}" || exit $?
|
||||
|
||||
if [[ "${DRY_RUN:-0}" == "1" ]]; then
|
||||
echo "DRY_RUN=1 -> skip latency/startup/throughput suites"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
run_latency_tests $QUICK_BENCHMARK_ROOT/tests/"${LATENCY_JSON:-latency-tests$ARCH.json}"
|
||||
run_startup_tests $QUICK_BENCHMARK_ROOT/tests/"${STARTUP_JSON:-startup-tests$ARCH.json}"
|
||||
run_throughput_tests $QUICK_BENCHMARK_ROOT/tests/"${THROUGHPUT_JSON:-throughput-tests$ARCH.json}"
|
||||
|
||||
# postprocess benchmarking results
|
||||
pip install tabulate pandas
|
||||
python3 $QUICK_BENCHMARK_ROOT/scripts/convert-results-json-to-markdown.py
|
||||
python3 $QUICK_BENCHMARK_ROOT/scripts/compare-json-results.py -f $RESULTS_FOLDER/benchmark_results.json
|
||||
|
||||
upload_to_buildkite
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@@ -1,21 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "llama8B_tp1_genai_perf",
|
||||
"qps_list": [4,8,16,32],
|
||||
"common_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-8B-Instruct",
|
||||
"tp": 1,
|
||||
"port": 8000,
|
||||
"num_prompts": 500,
|
||||
"reuse_server": false
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"gpu_memory_utilization": 0.9,
|
||||
"max_num_seqs": 512,
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"genai_perf_input_parameters": {
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -1,25 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "latency_llama8B_tp1",
|
||||
"environment_variables": {
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"dtype": "bfloat16",
|
||||
"distributed_executor_backend": "mp",
|
||||
"block_size": 128,
|
||||
"trust_remote_code": "",
|
||||
"disable_log_stats": "",
|
||||
"enforce_eager": "",
|
||||
"max_num_batched_tokens": 2048,
|
||||
"max_num_seqs": 256,
|
||||
"num_iters_warmup": 5,
|
||||
"num_iters": 15
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -1,25 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "latency_llama8B_tp2",
|
||||
"environment_variables": {
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_SGL_KERNEL": 1,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 2,
|
||||
"dtype": "bfloat16",
|
||||
"distributed_executor_backend": "mp",
|
||||
"block_size": 128,
|
||||
"trust_remote_code": "",
|
||||
"disable_log_stats": "",
|
||||
"enforce_eager": "",
|
||||
"max_num_batched_tokens": 2048,
|
||||
"max_num_seqs": 256,
|
||||
"num_iters_warmup": 5,
|
||||
"num_iters": 15
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -1,106 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "latency_llama8B_tp1",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"num-iters-warmup": 5,
|
||||
"num-iters": 15,
|
||||
"max-model-len": 256,
|
||||
"async-scheduling": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "latency_llama70B_tp4",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
||||
"tensor_parallel_size": 4,
|
||||
"load_format": "dummy",
|
||||
"num-iters-warmup": 5,
|
||||
"num-iters": 15,
|
||||
"max-model-len": 256,
|
||||
"async-scheduling": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "latency_mixtral8x7B_tp2",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
||||
"tensor_parallel_size": 2,
|
||||
"load_format": "dummy",
|
||||
"num-iters-warmup": 5,
|
||||
"num-iters": 15,
|
||||
"max-model-len": 256,
|
||||
"async-scheduling": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "latency_deepseek_r1",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "deepseek-ai/DeepSeek-R1",
|
||||
"tensor_parallel_size": 8,
|
||||
"load_format": "dummy",
|
||||
"max-model-len": 2048,
|
||||
"dtype": "bfloat16"
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "latency_llama4_maverick_17b128e_instruct_fp8",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
|
||||
"tensor_parallel_size": 8,
|
||||
"max-model-len": 512,
|
||||
"max-num-seqs": 128,
|
||||
"async-scheduling": "",
|
||||
"gpu-memory-utilization": 0.95,
|
||||
"enable_expert_parallel": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "latency_qwen3_8b",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "Qwen/Qwen3-8B",
|
||||
"tensor_parallel_size": 1,
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 128,
|
||||
"dtype": "bfloat16",
|
||||
"async-scheduling": ""
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -1,32 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "latency_llama8B_tp1",
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"num_iters_warmup": 5,
|
||||
"num_iters": 15
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "latency_llama70B_tp4",
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
||||
"tensor_parallel_size": 4,
|
||||
"load_format": "dummy",
|
||||
"num-iters-warmup": 5,
|
||||
"num-iters": 15
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "latency_mixtral8x7B_tp2",
|
||||
"parameters": {
|
||||
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
||||
"tensor_parallel_size": 2,
|
||||
"load_format": "dummy",
|
||||
"num-iters-warmup": 5,
|
||||
"num-iters": 15
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -1,311 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "llama8B_tp1_sharegpt",
|
||||
"qps_list": [4,8,16,32,"inf"],
|
||||
"common_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-8B-Instruct",
|
||||
"tp": 1,
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 500,
|
||||
"port": 8000,
|
||||
"reuse_server": false
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "bfloat16",
|
||||
"max_batch_size": 2048,
|
||||
"max_input_len": 4096,
|
||||
"max_seq_len": 6144,
|
||||
"max_num_tokens": 16384,
|
||||
"trt_llm_version": "v0.11.0"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"gpu_memory_utilization": 0.9,
|
||||
"max_num_seqs": 512,
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
},
|
||||
"sglang_server_parameters": {
|
||||
"disable_radix_cache": "",
|
||||
"enable_torch_compile": "",
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"sglang_client_parameters": {
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "llama8B_tp1_sonnet_512_16",
|
||||
"qps_list": [4,8,16,32,"inf"],
|
||||
"common_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-8B-Instruct",
|
||||
"tp": 1,
|
||||
"dataset_name": "sonnet",
|
||||
"dataset_path": "./sonnet_4x.txt",
|
||||
"num_prompts": 500,
|
||||
"port": 8000,
|
||||
"sonnet_input_len": 512,
|
||||
"sonnet_output_len": 16,
|
||||
"sonnet_prefix_len": 50,
|
||||
"reuse_server": true
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "bfloat16",
|
||||
"max_batch_size": 2048,
|
||||
"max_input_len": 4096,
|
||||
"max_seq_len": 6144,
|
||||
"max_num_tokens": 16384,
|
||||
"trt_llm_version": "v0.11.0"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"gpu_memory_utilization": 0.9,
|
||||
"max_num_seqs": 512,
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
},
|
||||
"sglang_server_parameters": {
|
||||
"disable_radix_cache": "",
|
||||
"enable_torch_compile": "",
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"sglang_client_parameters": {
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "llama8B_tp1_sonnet_512_256",
|
||||
"qps_list": [4,8,16,32,"inf"],
|
||||
"common_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-8B-Instruct",
|
||||
"tp": 1,
|
||||
"dataset_name": "sonnet",
|
||||
"dataset_path": "./sonnet_4x.txt",
|
||||
"num_prompts": 500,
|
||||
"port": 8000,
|
||||
"sonnet_input_len": 512,
|
||||
"sonnet_output_len": 256,
|
||||
"sonnet_prefix_len": 50,
|
||||
"reuse_server": true
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "bfloat16",
|
||||
"max_batch_size": 2048,
|
||||
"max_input_len": 4096,
|
||||
"max_seq_len": 6144,
|
||||
"max_num_tokens": 16384,
|
||||
"trt_llm_version": "v0.11.0"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"gpu_memory_utilization": 0.9,
|
||||
"max_num_seqs": 512,
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
},
|
||||
"sglang_server_parameters": {
|
||||
"disable_radix_cache": "",
|
||||
"enable_torch_compile": "",
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"sglang_client_parameters": {
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "llama70B_tp4_sharegpt",
|
||||
"qps_list": [4,8,16,32,"inf"],
|
||||
"common_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
|
||||
"tp": 4,
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 500,
|
||||
"port": 8000,
|
||||
"reuse_server": false
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "bfloat16",
|
||||
"max_batch_size": 2048,
|
||||
"max_input_len": 4096,
|
||||
"max_seq_len": 6144,
|
||||
"max_num_tokens": 16384,
|
||||
"trt_llm_version": "v0.11.0"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"gpu_memory_utilization": 0.9,
|
||||
"max_num_seqs": 512,
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
},
|
||||
"sglang_server_parameters": {
|
||||
"disable_radix_cache": "",
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"sglang_client_parameters": {
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "llama70B_tp4_sonnet_512_16",
|
||||
"qps_list": [4,8,16,32,"inf"],
|
||||
"common_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
|
||||
"tp": 4,
|
||||
"dataset_name": "sonnet",
|
||||
"dataset_path": "./sonnet_4x.txt",
|
||||
"num_prompts": 500,
|
||||
"port": 8000,
|
||||
"sonnet_input_len": 512,
|
||||
"sonnet_output_len": 16,
|
||||
"sonnet_prefix_len": 50,
|
||||
"reuse_server": true
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "bfloat16",
|
||||
"max_batch_size": 2048,
|
||||
"max_input_len": 4096,
|
||||
"max_seq_len": 6144,
|
||||
"max_num_tokens": 16384,
|
||||
"trt_llm_version": "v0.11.0"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"gpu_memory_utilization": 0.9,
|
||||
"max_num_seqs": 512,
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
},
|
||||
"sglang_server_parameters": {
|
||||
"disable_radix_cache": "",
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"sglang_client_parameters": {
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "llama70B_tp4_sonnet_512_256",
|
||||
"qps_list": [4,8,16,32,"inf"],
|
||||
"common_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
|
||||
"tp": 4,
|
||||
"dataset_name": "sonnet",
|
||||
"dataset_path": "./sonnet_4x.txt",
|
||||
"num_prompts": 500,
|
||||
"port": 8000,
|
||||
"sonnet_input_len": 512,
|
||||
"sonnet_output_len": 256,
|
||||
"sonnet_prefix_len": 50,
|
||||
"reuse_server": true
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "bfloat16",
|
||||
"max_batch_size": 2048,
|
||||
"max_input_len": 4096,
|
||||
"max_seq_len": 6144,
|
||||
"max_num_tokens": 16384,
|
||||
"trt_llm_version": "v0.11.0"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"gpu_memory_utilization": 0.9,
|
||||
"max_num_seqs": 512,
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
},
|
||||
"sglang_server_parameters": {
|
||||
"disable_radix_cache": "",
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"sglang_client_parameters": {
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -1,130 +0,0 @@
|
||||
{
|
||||
"defaults": {
|
||||
"qps_list": [
|
||||
"inf"
|
||||
],
|
||||
"max_concurrency_list": [
|
||||
12,
|
||||
16,
|
||||
24,
|
||||
32,
|
||||
64,
|
||||
128,
|
||||
200
|
||||
],
|
||||
"server_environment_variables": {
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_SGL_KERNEL": 1,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"dtype": "bfloat16",
|
||||
"distributed_executor_backend": "mp",
|
||||
"block_size": 128,
|
||||
"trust_remote_code": "",
|
||||
"disable_log_stats": "",
|
||||
"enforce_eager": "",
|
||||
"max_num_batched_tokens": 2048,
|
||||
"max_num_seqs": 256,
|
||||
"load_format": "dummy"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"backend": "vllm",
|
||||
"ignore-eos": "",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
"tests": [
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_sharegpt",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_sharegpt",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_128_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_128_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_128_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_2048_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_2048_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 128
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,37 +0,0 @@
|
||||
{
|
||||
"defaults": {
|
||||
"qps_list": [
|
||||
"inf"
|
||||
],
|
||||
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
|
||||
"server_environment_variables": {
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120
|
||||
},
|
||||
"server_parameters": {
|
||||
"dtype": "bfloat16",
|
||||
"model": "openai/whisper-large-v3-turbo"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "openai/whisper-large-v3-turbo",
|
||||
"backend": "openai-audio",
|
||||
"endpoint": "/v1/audio/transcriptions",
|
||||
"dataset_name": "hf",
|
||||
"dataset_path": "openslr/librispeech_asr",
|
||||
"hf_subset": "clean",
|
||||
"hf_split": "test",
|
||||
"no_stream": "",
|
||||
"no_oversample": "",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
"tests": [
|
||||
{
|
||||
"test_name": "serving_whisper_large_v3_turbo_librispeech_clean_tp1",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,40 +0,0 @@
|
||||
{
|
||||
"defaults": {
|
||||
"qps_list": [
|
||||
"inf"
|
||||
],
|
||||
"max_concurrency_list": [
|
||||
32,
|
||||
64,
|
||||
128
|
||||
],
|
||||
"server_environment_variables": {
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_SGL_KERNEL": 1,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"server_parameters": {
|
||||
"dtype": "bfloat16",
|
||||
"model": "jinaai/jina-embeddings-v3",
|
||||
"trust_remote_code": ""
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "jinaai/jina-embeddings-v3",
|
||||
"backend": "openai-embeddings",
|
||||
"endpoint": "/v1/embeddings",
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
"tests": [
|
||||
{
|
||||
"test_name": "serving_jina_embed_v3_tp1_sharegpt",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,288 +0,0 @@
|
||||
{
|
||||
"defaults": {
|
||||
"qps_list": [
|
||||
"inf"
|
||||
],
|
||||
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
|
||||
"server_environment_variables": {
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_SGL_KERNEL": 1,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"dtype": "bfloat16",
|
||||
"distributed_executor_backend": "mp",
|
||||
"block_size": 128,
|
||||
"trust_remote_code": "",
|
||||
"disable_log_stats": "",
|
||||
"max_num_batched_tokens": 2048,
|
||||
"max_num_seqs": 256
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"backend": "vllm",
|
||||
"ignore-eos": "",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
"tests": [
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_int4_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "hugging-quants/Meta-Llama-3.1-8B-Instruct-AWQ-INT4",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_int8_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "RedHatAI/Meta-Llama-3.1-8B-Instruct-quantized.w8a8",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama1B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-3.2-1B"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-3.2-1B",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama3B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-3.2-3B-Instruct"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-3.2-3B-Instruct",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama70B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-3.3-70B-Instruct"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_granite2B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "ibm-granite/granite-3.2-2b-instruct"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "ibm-granite/granite-3.2-2b-instruct",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_qwen1.7B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "Qwen/Qwen3-1.7B"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "Qwen/Qwen3-1.7B",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_qwen4B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "Qwen/Qwen3-4B"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "Qwen/Qwen3-4B",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_qwen8B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "Qwen/Qwen3-8B"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "Qwen/Qwen3-8B",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_qwen14B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "Qwen/Qwen3-14B"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "Qwen/Qwen3-14B",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_qwen30B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "Qwen/Qwen3-30B-A3B"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "Qwen/Qwen3-30B-A3B",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_glm9B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "zai-org/glm-4-9b-hf"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "zai-org/glm-4-9b-hf",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_gemma7B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "google/gemma-7b"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "google/gemma-7b",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_gemma3-4b_tp1_random_128_128",
|
||||
"server_environment_variables": {
|
||||
"VLLM_CPU_SGL_KERNEL": 0
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "google/gemma-3-4b-it"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "google/gemma-3-4b-it",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_gemma3-12b_tp1_random_128_128",
|
||||
"server_environment_variables": {
|
||||
"VLLM_CPU_SGL_KERNEL": 0
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "google/gemma-3-12b-it"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "google/gemma-3-12b-it",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_gemma4-4b_tp1_random_128_128",
|
||||
"server_environment_variables": {
|
||||
"VLLM_CPU_SGL_KERNEL": 0
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "google/gemma-4-E4B-it"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "google/gemma-4-E4B-it",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_gemma4-2b_tp1_random_128_128",
|
||||
"server_environment_variables": {
|
||||
"VLLM_CPU_SGL_KERNEL": 0
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "google/gemma-4-E2B-it"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "google/gemma-4-E2B-it",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_gemma4-26b_tp1_random_128_128",
|
||||
"server_environment_variables": {
|
||||
"VLLM_CPU_SGL_KERNEL": 0,
|
||||
"VLLM_CPU_ATTN_SPLIT_KV": 0
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "google/gemma-4-26B-A4B-it"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "google/gemma-4-26B-A4B-it",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_phi4_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "microsoft/Phi-4-reasoning"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "microsoft/Phi-4-reasoning",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,142 +0,0 @@
|
||||
{
|
||||
"defaults": {
|
||||
"qps_list": [
|
||||
"inf"
|
||||
],
|
||||
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
|
||||
"server_environment_variables": {
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_SGL_KERNEL": 1,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"dtype": "bfloat16",
|
||||
"distributed_executor_backend": "mp",
|
||||
"block_size": 128,
|
||||
"trust_remote_code": "",
|
||||
"disable_log_stats": "",
|
||||
"max_num_batched_tokens": 2048,
|
||||
"max_num_seqs": 256
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"backend": "vllm",
|
||||
"ignore-eos": "",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
"tests": [
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_sharegpt",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_sharegpt",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_128_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_128_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_128_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_2048_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_2048_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_2048_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp2_random_2048_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 2
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,163 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_sharegpt",
|
||||
"qps_list": [1, 4, 16, "inf"],
|
||||
"server_environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"disable_log_stats": "",
|
||||
"load_format": "dummy",
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 256,
|
||||
"async-scheduling": ""
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
||||
"backend": "vllm",
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama70B_tp4_sharegpt",
|
||||
"qps_list": [1, 4, 16, "inf"],
|
||||
"server_environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
||||
"tensor_parallel_size": 4,
|
||||
"disable_log_stats": "",
|
||||
"load_format": "dummy",
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 256,
|
||||
"async-scheduling": ""
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
||||
"backend": "vllm",
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_mixtral8x7B_tp2_sharegpt",
|
||||
"qps_list": [1, 4, 16, "inf"],
|
||||
"server_environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
||||
"tensor_parallel_size": 2,
|
||||
"disable_log_stats": "",
|
||||
"load_format": "dummy",
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 256,
|
||||
"async-scheduling": ""
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
||||
"backend": "vllm",
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_deepseek_r1",
|
||||
"qps_list": [1, 4, 16, "inf"],
|
||||
"server_environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "deepseek-ai/DeepSeek-R1",
|
||||
"tensor_parallel_size": 8,
|
||||
"disable_log_stats": "",
|
||||
"load_format": "dummy",
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 200,
|
||||
"async-scheduling": "",
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "deepseek-ai/DeepSeek-R1",
|
||||
"backend": "vllm",
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama4_maverick_17b128e_instruct_fp8",
|
||||
"qps_list": [1, 4, 16, "inf"],
|
||||
"server_environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
|
||||
"tensor_parallel_size": 8,
|
||||
"disable_log_stats": "",
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 128,
|
||||
"async-scheduling": "",
|
||||
"enable_expert_parallel": "",
|
||||
"max-num-batched-tokens": 4096
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
|
||||
"backend": "vllm",
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_qwen3_8b",
|
||||
"qps_list": [1, 4, 10, "inf"],
|
||||
"server_environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"server_parameters": {
|
||||
"model": "Qwen/Qwen-3-8B",
|
||||
"tensor_parallel_size": 1,
|
||||
"dtype": "bfloat16",
|
||||
"disable_log_stats": "",
|
||||
"async-scheduling": ""
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "Qwen/Qwen-3-8B",
|
||||
"backend": "vllm",
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -1,112 +0,0 @@
|
||||
{
|
||||
"defaults": {
|
||||
"qps_list": [
|
||||
"inf"
|
||||
],
|
||||
"max_concurrency_list": [12, 16, 24, 32, 64, 128, 200],
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"dtype": "bfloat16"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"backend": "vllm",
|
||||
"ignore-eos": "",
|
||||
"temperature": 0,
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
"tests": [
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_sharegpt",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
|
||||
}
|
||||
},
|
||||
{
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json"
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_128_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_2048_128",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama8B_tp1_random_2048_2048",
|
||||
"server_parameters": {
|
||||
"tensor_parallel_size": 1
|
||||
},
|
||||
"client_parameters": {
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 2048,
|
||||
"random-output-len": 2048
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama70B_tp4_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"async_scheduling": "",
|
||||
"no_enable_prefix_caching": "",
|
||||
"max_num_batched_tokens": 8192
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Llama-3.3-70B-Instruct",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_gemma4-e4b_tp1_random_128_128",
|
||||
"server_parameters": {
|
||||
"model": "google/gemma-4-E4B-it",
|
||||
"enable_auto_tool_choice": "",
|
||||
"tool_call_parser": "gemma4",
|
||||
"chat_template": "examples/tool_chat_template_gemma4.jinja",
|
||||
"reasoning_parser": "gemma4"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "google/gemma-4-E4B-it",
|
||||
"dataset_name": "random",
|
||||
"random-input-len": 128,
|
||||
"random-output-len": 128
|
||||
}
|
||||
}
|
||||
]
|
||||
}
|
||||
@@ -1,26 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "throughput_llama8B_tp1",
|
||||
"environment_variables": {
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"dtype": "bfloat16",
|
||||
"distributed_executor_backend": "mp",
|
||||
"block_size": 128,
|
||||
"trust_remote_code": "",
|
||||
"disable_log_stats": "",
|
||||
"enforce_eager": "",
|
||||
"max_num_batched_tokens": 2048,
|
||||
"max_num_seqs": 256,
|
||||
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 200,
|
||||
"backend": "vllm"
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -1,26 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "throughput_llama8B_tp2",
|
||||
"environment_variables": {
|
||||
"VLLM_ALLOW_LONG_MAX_MODEL_LEN": 1,
|
||||
"VLLM_ENGINE_ITERATION_TIMEOUT_S": 120,
|
||||
"VLLM_CPU_SGL_KERNEL": 1,
|
||||
"VLLM_CPU_KVCACHE_SPACE": 40
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 2,
|
||||
"dtype": "bfloat16",
|
||||
"distributed_executor_backend": "mp",
|
||||
"block_size": 128,
|
||||
"trust_remote_code": "",
|
||||
"disable_log_stats": "",
|
||||
"enforce_eager": "",
|
||||
"max_num_batched_tokens": 2048,
|
||||
"max_num_seqs": 256,
|
||||
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 200,
|
||||
"backend": "vllm"
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -1,123 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "throughput_llama8B_tp1",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 1000,
|
||||
"backend": "vllm",
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 512,
|
||||
"async-scheduling": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "throughput_llama70B_tp4",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
||||
"tensor_parallel_size": 4,
|
||||
"load_format": "dummy",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 1000,
|
||||
"backend": "vllm",
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 512,
|
||||
"async-scheduling": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "throughput_mixtral8x7B_tp2",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
||||
"tensor_parallel_size": 2,
|
||||
"load_format": "dummy",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 1000,
|
||||
"backend": "vllm",
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 512,
|
||||
"async-scheduling": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "throughput_deepseek_r1",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "deepseek-ai/DeepSeek-R1",
|
||||
"tensor_parallel_size": 8,
|
||||
"load_format": "dummy",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"dataset_name": "sharegpt",
|
||||
"num_prompts": 1000,
|
||||
"backend": "vllm",
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 384,
|
||||
"async-scheduling": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "throughput_llama4_maverick_17b128e_instruct_fp8",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8",
|
||||
"tensor_parallel_size": 8,
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"dataset_name": "sharegpt",
|
||||
"num_prompts": 1000,
|
||||
"backend": "vllm",
|
||||
"max-model-len": 2048,
|
||||
"max-num-seqs": 512,
|
||||
"async-scheduling": "",
|
||||
"enable_expert_parallel": ""
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "throughput_qwen3_8b",
|
||||
"environment_variables": {
|
||||
"PT_HPU_LAZY_MODE": 1,
|
||||
"PT_HPU_ENABLE_LAZY_COLLECTIVES": 1,
|
||||
"VLLM_CONTIGUOUS_PA": 1,
|
||||
"VLLM_DEFRAG": 1
|
||||
},
|
||||
"parameters": {
|
||||
"model": "Qwen/Qwen-3-8B",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"dataset_name": "sharegpt",
|
||||
"num_prompts": 1000,
|
||||
"max-num-seqs": 512,
|
||||
"backend": "vllm",
|
||||
"async-scheduling": ""
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -1,35 +0,0 @@
|
||||
[
|
||||
{
|
||||
"test_name": "throughput_llama8B_tp1",
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 200,
|
||||
"backend": "vllm"
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "throughput_llama70B_tp4",
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
||||
"tensor_parallel_size": 4,
|
||||
"load_format": "dummy",
|
||||
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 200,
|
||||
"backend": "vllm"
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "throughput_mixtral8x7B_tp2",
|
||||
"parameters": {
|
||||
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
||||
"tensor_parallel_size": 2,
|
||||
"load_format": "dummy",
|
||||
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 200,
|
||||
"backend": "vllm"
|
||||
}
|
||||
}
|
||||
]
|
||||
File diff suppressed because it is too large
Load Diff
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user