forked from Karylab-cklius/vllm
Compare commits
1
Commits
| Author | SHA1 | Date | |
|---|---|---|---|
 youkaichao
|
617fb893d5 |
@@ -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 = 250
|
||||
|
||||
|
||||
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"
|
||||
@@ -1,23 +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/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"
|
||||
@@ -1,75 +0,0 @@
|
||||
group: Hardware - AMD Build
|
||||
steps:
|
||||
# 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: []
|
||||
device: amd_cpu
|
||||
no_plugin: true
|
||||
commands:
|
||||
- bash .buildkite/scripts/ci-bake-rocm.sh ci-base-rocm-ci-with-deps
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
VLLM_BAKE_FILE: "docker/docker-bake-rocm.hcl"
|
||||
PYTORCH_ROCM_ARCH: "gfx90a;gfx942;gfx950"
|
||||
REMOTE_VLLM: "1"
|
||||
VLLM_BRANCH: "$BUILDKITE_COMMIT"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # Agent was lost
|
||||
limit: 1
|
||||
- exit_status: -10 # Agent was lost
|
||||
limit: 1
|
||||
|
||||
- label: "AMD: :docker: build test image and artifacts"
|
||||
key: image-build-amd
|
||||
soft_fail: false
|
||||
depends_on:
|
||||
- ensure-ci-base-amd
|
||||
device: amd_cpu
|
||||
no_plugin: true
|
||||
commands:
|
||||
- |
|
||||
if [[ "${ROCM_CI_ARTIFACT_ONLY:-0}" == "1" ]]; then
|
||||
echo "ROCM_CI_ARTIFACT_ONLY=1; building ROCm wheel artifact only"
|
||||
IMAGE_TAG="" bash .buildkite/scripts/ci-bake-rocm.sh test-rocm-ci-with-artifacts
|
||||
else
|
||||
bash .buildkite/scripts/ci-bake-rocm.sh test-rocm-ci-with-wheel
|
||||
fi
|
||||
- |
|
||||
docker run --rm --network=none --entrypoint /bin/bash "rocm/vllm-ci:${BUILDKITE_COMMIT}" -ec '
|
||||
if [ ! -d /vllm-workspace ]; then echo Missing directory: /vllm-workspace >&2; exit 1; fi
|
||||
if [ ! -d /vllm-workspace/tests ]; then echo Missing directory: /vllm-workspace/tests >&2; exit 1; fi
|
||||
if [ ! -d /vllm-workspace/src/vllm ]; then echo Missing directory: /vllm-workspace/src/vllm >&2; exit 1; fi
|
||||
if [ ! -x /vllm-workspace/src/vllm/vllm-rs ]; then echo Missing executable: /vllm-workspace/src/vllm/vllm-rs >&2; exit 1; fi
|
||||
command -v python3
|
||||
command -v uv
|
||||
command -v pytest
|
||||
if ! command -v amd-smi >/dev/null 2>&1 && ! command -v rocminfo >/dev/null 2>&1; then
|
||||
echo No ROCm CLI found in image >&2
|
||||
exit 1
|
||||
fi
|
||||
python3 - <<PY
|
||||
import torch, vllm
|
||||
print(torch.__version__)
|
||||
print(vllm.__version__)
|
||||
PY
|
||||
echo AMD image smoke OK
|
||||
'
|
||||
env:
|
||||
DOCKER_BUILDKIT: "1"
|
||||
VLLM_BAKE_FILE: "docker/docker-bake-rocm.hcl"
|
||||
PYTORCH_ROCM_ARCH: "gfx90a;gfx942;gfx950"
|
||||
IMAGE_TAG: "rocm/vllm-ci:$BUILDKITE_COMMIT"
|
||||
REMOTE_VLLM: "1"
|
||||
VLLM_BRANCH: "$BUILDKITE_COMMIT"
|
||||
retry:
|
||||
automatic:
|
||||
- exit_status: -1 # 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
|
||||
@@ -1,153 +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
|
||||
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"
|
||||
|
||||
# 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 -m cpu_model --num-shards=$$BUILDKITE_PARALLEL_JOB_COUNT --shard-id=$$BUILDKITE_PARALLEL_JOB"
|
||||
parallelism: 4
|
||||
|
||||
- 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: 30
|
||||
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: 30
|
||||
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: 30
|
||||
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'
|
||||
@@ -1,256 +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 "${BUILDER_NAME}" --driver docker-container --use
|
||||
docker buildx inspect --bootstrap
|
||||
fi
|
||||
|
||||
# builder info
|
||||
echo "Active builder:"
|
||||
docker buildx ls | grep -E '^\*|^NAME' || docker buildx ls
|
||||
}
|
||||
|
||||
check_and_skip_if_image_exists() {
|
||||
if [[ -n "${IMAGE_TAG:-}" ]]; then
|
||||
echo "--- :mag: Checking if image exists"
|
||||
if docker manifest inspect "${IMAGE_TAG}" >/dev/null 2>&1; then
|
||||
echo "Image already exists: ${IMAGE_TAG}"
|
||||
echo "Skipping build"
|
||||
exit 0
|
||||
fi
|
||||
echo "Image not found, proceeding with build"
|
||||
fi
|
||||
}
|
||||
|
||||
ecr_login() {
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$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
|
||||
|
||||
# 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"
|
||||
@@ -1,130 +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 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
|
||||
@@ -1,38 +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=$3
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
|
||||
|
||||
# skip build if image already exists
|
||||
if [[ -z $(docker manifest inspect "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64) ]]; then
|
||||
echo "Image not found, proceeding with build..."
|
||||
else
|
||||
echo "Image found"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# build for arm64 GPU targets: Grace/GH200 (sm_90) 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 12.0" \
|
||||
--build-arg USE_SCCACHE=1 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--tag "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64 \
|
||||
--target test \
|
||||
--progress plain .
|
||||
|
||||
# push
|
||||
docker push "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64
|
||||
@@ -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=$3
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
|
||||
|
||||
# skip build if image already exists
|
||||
if [[ -z $(docker manifest inspect "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-cpu) ]]; then
|
||||
echo "Image not found, proceeding with build..."
|
||||
else
|
||||
echo "Image found"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# build
|
||||
docker build --file docker/Dockerfile.cpu \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--build-arg VLLM_CPU_X86=true \
|
||||
--tag "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-cpu \
|
||||
--target vllm-test \
|
||||
--progress plain .
|
||||
|
||||
# push
|
||||
docker push "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-cpu
|
||||
@@ -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=$3
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
|
||||
|
||||
# skip build if image already exists
|
||||
if [[ -z $(docker manifest inspect "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64-cpu) ]]; then
|
||||
echo "Image not found, proceeding with build..."
|
||||
else
|
||||
echo "Image found"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# build
|
||||
docker build --file docker/Dockerfile.cpu \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--tag "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64-cpu \
|
||||
--target vllm-test \
|
||||
--progress plain .
|
||||
|
||||
# push
|
||||
docker push "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-arm64-cpu
|
||||
@@ -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=$3
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$REGISTRY" || true
|
||||
|
||||
# skip build if image already exists
|
||||
if [[ -z $(docker manifest inspect "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-hpu) ]]; then
|
||||
echo "Image not found, proceeding with build..."
|
||||
else
|
||||
echo "Image found"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# build
|
||||
docker build \
|
||||
--file tests/pytorch_ci_hud_benchmark/Dockerfile.hpu \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--tag "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-hpu \
|
||||
--progress plain \
|
||||
https://github.com/vllm-project/vllm-gaudi.git
|
||||
|
||||
# push
|
||||
docker push "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-hpu
|
||||
@@ -1,68 +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: $IMAGE_TAG — skipping build"
|
||||
exit 0
|
||||
fi
|
||||
echo "Image not found, proceeding with build..."
|
||||
|
||||
# --- CUDA 13.0 for nightly builds ---
|
||||
# Nightly CI uses CUDA 13.0 while regular CI stays on CUDA 12.9
|
||||
NIGHTLY_CUDA_VERSION="13.0.2"
|
||||
NIGHTLY_BUILD_BASE_IMAGE="nvidia/cuda:${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"
|
||||
@@ -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=$3
|
||||
|
||||
# authenticate with AWS ECR
|
||||
aws ecr-public get-login-password --region us-east-1 | docker login --username AWS --password-stdin "$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 "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-xpu &> /dev/null; then
|
||||
echo "Image not found, proceeding with build..."
|
||||
else
|
||||
echo "Image found"
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# build
|
||||
docker build \
|
||||
--file docker/Dockerfile.xpu \
|
||||
--build-arg max_jobs=16 \
|
||||
--build-arg buildkite_commit="$BUILDKITE_COMMIT" \
|
||||
--tag "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-xpu \
|
||||
--progress plain .
|
||||
|
||||
# push
|
||||
docker push "$REGISTRY"/"$REPO":"$BUILDKITE_COMMIT"-xpu
|
||||
@@ -1,27 +0,0 @@
|
||||
group: Basic Correctness
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: XPU Sleep Mode
|
||||
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/
|
||||
- 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: 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_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'
|
||||
@@ -1,263 +0,0 @@
|
||||
group: Miscellaneous Intel
|
||||
depends_on:
|
||||
- image-build-xpu
|
||||
steps:
|
||||
- label: V1 Core + KV + Metrics
|
||||
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/
|
||||
- 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: 30
|
||||
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/test_topk_topp_sampler.py &&
|
||||
pytest -v -s v1/sample/test_logprobs.py &&
|
||||
pytest -v -s v1/sample/test_logprobs_e2e.py'
|
||||
|
||||
- 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: 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/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: 30
|
||||
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: 30
|
||||
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: 50
|
||||
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: 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/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: 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/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: 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
|
||||
'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: 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
|
||||
- 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]"'
|
||||
|
||||
@@ -1,170 +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: 30
|
||||
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: 30
|
||||
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/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: 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
|
||||
'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'
|
||||
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
@@ -10,4 +9,3 @@ tasks:
|
||||
value: 0.664
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
trust_remote_code: True
|
||||
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
-1
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
-1
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
-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
|
||||
-1
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
-1
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
# 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
|
||||
# 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 -t 1
|
||||
model_name: "meta-llama/Meta-Llama-3-8B-Instruct"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
|
||||
@@ -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
|
||||
@@ -1,14 +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"
|
||||
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
|
||||
@@ -0,0 +1,11 @@
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nvidia/Minitron-4B-Base -b auto -l 1000 -f 5 -t 1
|
||||
model_name: "nvidia/Minitron-4B-Base"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.252
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.252
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
@@ -1,5 +1,4 @@
|
||||
# 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
|
||||
# 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 -t 4
|
||||
model_name: "mistralai/Mixtral-8x7B-Instruct-v0.1"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
|
||||
@@ -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
|
||||
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
@@ -0,0 +1,11 @@
|
||||
# bash .buildkite/lm-eval-harness/run-lm-eval-gsm-vllm-baseline.sh -m nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise -b "auto" -l 1000 -f 5 -t 1
|
||||
model_name: "nm-testing/Qwen2-1.5B-Instruct-W8A16-Channelwise"
|
||||
tasks:
|
||||
- name: "gsm8k"
|
||||
metrics:
|
||||
- name: "exact_match,strict-match"
|
||||
value: 0.595
|
||||
- name: "exact_match,flexible-extract"
|
||||
value: 0.582
|
||||
limit: 1000
|
||||
num_fewshot: 5
|
||||
@@ -1,4 +1,3 @@
|
||||
# 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:
|
||||
|
||||
@@ -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
|
||||
@@ -3,4 +3,3 @@ 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 +1,9 @@
|
||||
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.yaml
|
||||
Meta-Llama-3-8B-Instruct-FP8.yaml
|
||||
Meta-Llama-3-8B-Instruct-FP8-compressed-tensors.yaml
|
||||
Meta-Llama-3-8B-Instruct-INT8-compressed-tensors.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
|
||||
Meta-Llama-3-8B-Instruct-Channelwise-compressed-tensors.yaml
|
||||
Minitron-4B-Base.yaml
|
||||
Qwen2-1.5B-Instruct-INT8-compressed-tensors.yaml
|
||||
Qwen2-1.5B-Instruct-FP8W8.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 "$LIMIT"
|
||||
Executable → Regular
+4
-4
@@ -2,7 +2,7 @@
|
||||
# We can use this script to compute baseline accuracy on GSM for transformers.
|
||||
#
|
||||
# Make sure you have lm-eval-harness installed:
|
||||
# pip install "lm-eval[api]>=0.4.12"
|
||||
# pip install git+https://github.com/EleutherAI/lm-evaluation-harness.git@9516087b81a61d0e220b22cc1b75be76de23bc10
|
||||
|
||||
usage() {
|
||||
echo``
|
||||
@@ -41,6 +41,6 @@ while getopts "m:b:l:f:" OPT; do
|
||||
done
|
||||
|
||||
lm_eval --model hf \
|
||||
--model_args "pretrained=$MODEL,parallelize=True" \
|
||||
--tasks gsm8k --num_fewshot "$FEWSHOT" --limit "$LIMIT" \
|
||||
--batch_size "$BATCH_SIZE"
|
||||
--model_args pretrained=$MODEL,parallelize=True \
|
||||
--tasks gsm8k --num_fewshot $FEWSHOT --limit $LIMIT \
|
||||
--batch_size $BATCH_SIZE
|
||||
|
||||
@@ -3,7 +3,7 @@
|
||||
# We use this for fp8, which HF does not support.
|
||||
#
|
||||
# Make sure you have lm-eval-harness installed:
|
||||
# pip install "lm-eval[api]>=0.4.12"
|
||||
# pip install lm-eval==0.4.3
|
||||
|
||||
usage() {
|
||||
echo``
|
||||
@@ -46,6 +46,6 @@ while getopts "m:b:l:f:t:" OPT; do
|
||||
done
|
||||
|
||||
lm_eval --model vllm \
|
||||
--model_args "pretrained=$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"
|
||||
--model_args pretrained=$MODEL,tensor_parallel_size=$TP_SIZE,distributed_executor_backend="ray",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
|
||||
@@ -0,0 +1,59 @@
|
||||
#!/bin/bash
|
||||
|
||||
usage() {
|
||||
echo``
|
||||
echo "Runs lm eval harness on GSM8k using vllm and compares to "
|
||||
echo "precomputed baseline (measured by HF transformers.)"
|
||||
echo
|
||||
echo "usage: ${0} <options>"
|
||||
echo
|
||||
echo " -c - path to the test data config (e.g. configs/small-models.txt)"
|
||||
echo " -t - tensor parallel size"
|
||||
echo
|
||||
}
|
||||
|
||||
SUCCESS=0
|
||||
|
||||
while getopts "c:t:" OPT; do
|
||||
case ${OPT} in
|
||||
c )
|
||||
CONFIG="$OPTARG"
|
||||
;;
|
||||
t )
|
||||
TP_SIZE="$OPTARG"
|
||||
;;
|
||||
\? )
|
||||
usage
|
||||
exit 1
|
||||
;;
|
||||
esac
|
||||
done
|
||||
|
||||
# Parse list of configs.
|
||||
IFS=$'\n' read -d '' -r -a MODEL_CONFIGS < $CONFIG
|
||||
|
||||
for MODEL_CONFIG in "${MODEL_CONFIGS[@]}"
|
||||
do
|
||||
LOCAL_SUCCESS=0
|
||||
|
||||
echo "=== RUNNING MODEL: $MODEL_CONFIG WITH TP SIZE: $TP_SIZE==="
|
||||
|
||||
export LM_EVAL_TEST_DATA_FILE=$PWD/configs/${MODEL_CONFIG}
|
||||
export LM_EVAL_TP_SIZE=$TP_SIZE
|
||||
pytest -s test_lm_eval_correctness.py || LOCAL_SUCCESS=$?
|
||||
|
||||
if [[ $LOCAL_SUCCESS == 0 ]]; then
|
||||
echo "=== PASSED MODEL: ${MODEL_CONFIG} ==="
|
||||
else
|
||||
echo "=== FAILED MODEL: ${MODEL_CONFIG} ==="
|
||||
fi
|
||||
|
||||
SUCCESS=$((SUCCESS + LOCAL_SUCCESS))
|
||||
|
||||
done
|
||||
|
||||
if [ "${SUCCESS}" -eq "0" ]; then
|
||||
exit 0
|
||||
else
|
||||
exit 1
|
||||
fi
|
||||
@@ -1,149 +1,55 @@
|
||||
# SPDX-License-Identifier: Apache-2.0
|
||||
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
|
||||
"""
|
||||
LM eval harness on model to compare vs HF baseline computed offline.
|
||||
Configs are found in configs/$MODEL.yaml
|
||||
|
||||
pytest -s -v test_lm_eval_correctness.py \
|
||||
--config-list-file=configs/models-small.txt \
|
||||
--tp-size=1
|
||||
* export LM_EVAL_TEST_DATA_FILE=configs/Meta-Llama-3-70B-Instruct.yaml
|
||||
* export LM_EVAL_TP_SIZE=4
|
||||
* pytest -s test_lm_eval_correctness.py
|
||||
"""
|
||||
|
||||
import os
|
||||
from contextlib import contextmanager
|
||||
from pathlib import Path
|
||||
|
||||
import lm_eval
|
||||
import pytest
|
||||
import numpy
|
||||
import yaml
|
||||
|
||||
from vllm.platforms import current_platform
|
||||
RTOL = 0.02
|
||||
TEST_DATA_FILE = os.environ.get(
|
||||
"LM_EVAL_TEST_DATA_FILE",
|
||||
".buildkite/lm-eval-harness/configs/Meta-Llama-3-8B-Instruct.yaml")
|
||||
|
||||
DEFAULT_RTOL = 0.08
|
||||
TP_SIZE = os.environ.get("LM_EVAL_TP_SIZE", 1)
|
||||
|
||||
|
||||
@contextmanager
|
||||
def scoped_env_vars(new_env: dict[str, str]):
|
||||
if not new_env:
|
||||
# Fast path: nothing to do
|
||||
yield
|
||||
return
|
||||
def launch_lm_eval(eval_config):
|
||||
model_args = f"pretrained={eval_config['model_name']}," \
|
||||
f"tensor_parallel_size={TP_SIZE}," \
|
||||
f"add_bos_token=true"
|
||||
|
||||
old_values = {}
|
||||
new_keys = []
|
||||
results = lm_eval.simple_evaluate(
|
||||
model="vllm",
|
||||
model_args=model_args,
|
||||
tasks=[task["name"] for task in eval_config["tasks"]],
|
||||
num_fewshot=eval_config["num_fewshot"],
|
||||
limit=eval_config["limit"],
|
||||
batch_size="auto")
|
||||
|
||||
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},"
|
||||
|
||||
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.
|
||||
def test_lm_eval_correctness():
|
||||
eval_config = yaml.safe_load(
|
||||
Path(TEST_DATA_FILE).read_text(encoding="utf-8"))
|
||||
|
||||
Model YAML configs can specify::
|
||||
# Launch eval requests.
|
||||
results = launch_lm_eval(eval_config)
|
||||
|
||||
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
|
||||
# Confirm scores match ground truth.
|
||||
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
|
||||
print(f'{task["name"]} | {metric["name"]}: '
|
||||
f'ground_truth={ground_truth} | measured={measured_value}')
|
||||
assert numpy.isclose(ground_truth, measured_value, rtol=RTOL)
|
||||
|
||||
@@ -0,0 +1,152 @@
|
||||
# vLLM benchmark suite
|
||||
|
||||
|
||||
## Introduction
|
||||
|
||||
This directory contains two sets of benchmark for vllm.
|
||||
- Performance benchmark: benchmark vllm's performance under various workload, for **developers** to gain clarity on whether their PR improves/degrades vllm's performance
|
||||
- Nightly benchmark: compare vllm's performance against alternatives (tgi, trt-llm and lmdeploy), for **the public** to know when to choose vllm.
|
||||
|
||||
|
||||
See [vLLM performance dashboard](https://perf.vllm.ai) for the latest performance benchmark results and [vLLM GitHub README](https://github.com/vllm-project/vllm/blob/main/README.md) for latest nightly benchmark results.
|
||||
|
||||
|
||||
## Performance benchmark quick overview
|
||||
|
||||
**Benchmarking Coverage**: latency, throughput and fix-qps serving on A100 (the support for FP8 benchmark on H100 is coming!), 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.
|
||||
|
||||
|
||||
## Nightly benchmark quick overview
|
||||
|
||||
**Benchmarking Coverage**: Fix-qps serving on A100 (the support for FP8 benchmark on H100 is coming!) on Llama-3 8B, 70B and Mixtral 8x7B.
|
||||
|
||||
**Benchmarking engines**: vllm, TGI, trt-llm and lmdeploy.
|
||||
|
||||
**Benchmarking Duration**: about 3.5hrs.
|
||||
|
||||
|
||||
|
||||
## Trigger the benchmark
|
||||
|
||||
Performance benchmark will be triggered when:
|
||||
- A PR being merged into vllm.
|
||||
- Every commit for those PRs with `perf-benchmarks` label.
|
||||
|
||||
Nightly benchmark will be triggered when:
|
||||
- Every commit for those PRs with `nightly-benchmarks` label.
|
||||
|
||||
|
||||
|
||||
|
||||
## Performance benchmark details
|
||||
|
||||
See [descriptions.md](tests/descriptions.md) for detailed descriptions, and use `tests/latency-tests.json`, `tests/throughput-tests.json`, `tests/serving-tests.json` to configure the test cases.
|
||||
|
||||
|
||||
#### 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 `benchmark_latency.py`. Note that please use underline `_` instead of the dash `-` when specifying the command line arguments, and `run-benchmarks-suite.sh` will convert the underline to dash when feeding the arguments to `benchmark_latency.py`. For example, the corresponding command line arguments for `benchmark_latency.py` 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 `benchmark_throughput.py`.
|
||||
|
||||
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 `benchmark_serving.py` with request rate = inf to cover the online serving overhead. The corresponding parameters are in `serving-tests.json`, and here is an example:
|
||||
|
||||
```
|
||||
[
|
||||
{
|
||||
"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,
|
||||
"swap_space": 16,
|
||||
"disable_log_stats": "",
|
||||
"disable_log_requests": "",
|
||||
"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 `benchmark_serving.py`.
|
||||
- The `qps_list` controls the list of qps for test. It will be used to configure the `--request-rate` parameter in `benchmark_serving.py`
|
||||
|
||||
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`.
|
||||
|
||||
#### Visualizing the results
|
||||
The `convert-results-json-to-markdown.py` helps you put the benchmarking results inside a markdown table, by formatting [descriptions.md](tests/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.
|
||||
|
||||
|
||||
|
||||
## Nightly test details
|
||||
|
||||
See [nightly-descriptions.md](nightly-descriptions.md) for the detailed description on test workload, models and docker containers of benchmarking other llm engines.
|
||||
|
||||
|
||||
#### Workflow
|
||||
|
||||
- The [nightly-pipeline.yaml](nightly-pipeline.yaml) specifies the docker containers for different LLM serving engines.
|
||||
- Inside each container, we run [run-nightly-suite.sh](run-nightly-suite.sh), which will probe the serving engine of the current container.
|
||||
- The `run-nightly-suite.sh` will redirect the request to `tests/run-[llm serving engine name]-nightly.sh`, which parses the workload described in [nightly-tests.json](tests/nightly-tests.json) and performs the benchmark.
|
||||
- At last, we run [scripts/plot-nightly-results.py](scripts/plot-nightly-results.py) to collect and plot the final benchmarking results, and update the results to buildkite.
|
||||
|
||||
#### Nightly tests
|
||||
|
||||
In [nightly-tests.json](tests/nightly-tests.json), we include the command line arguments for benchmarking commands, together with the benchmarking test cases. The format is highly similar to performance benchmark.
|
||||
|
||||
#### Docker containers
|
||||
|
||||
The docker containers for benchmarking are specified in `nightly-pipeline.yaml`.
|
||||
|
||||
WARNING: the docker versions are HARD-CODED and SHOULD BE ALIGNED WITH `nightly-descriptions.md`. The docker versions need to be hard-coded as there are several version-specific bug fixes inside `tests/run-[llm serving engine name]-nightly.sh`.
|
||||
|
||||
WARNING: populating `trt-llm` to latest version is not easy, as it requires updating several protobuf files in [tensorrt-demo](https://github.com/neuralmagic/tensorrt-demo.git).
|
||||
|
||||
@@ -0,0 +1,61 @@
|
||||
steps:
|
||||
- label: "Wait for container to be ready"
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
containers:
|
||||
- image: badouralix/curl-jq
|
||||
command:
|
||||
- sh
|
||||
- .buildkite/nightly-benchmarks/scripts/wait-for-image.sh
|
||||
- wait
|
||||
- label: "A100"
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
priorityClassName: perf-benchmark
|
||||
containers:
|
||||
- image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
|
||||
command:
|
||||
- bash .buildkite/nightly-benchmarks/run-benchmarks-suite.sh
|
||||
resources:
|
||||
limits:
|
||||
nvidia.com/gpu: 8
|
||||
volumeMounts:
|
||||
- name: devshm
|
||||
mountPath: /dev/shm
|
||||
env:
|
||||
- name: VLLM_USAGE_SOURCE
|
||||
value: ci-test
|
||||
- name: HF_TOKEN
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: hf-token-secret
|
||||
key: token
|
||||
nodeSelector:
|
||||
nvidia.com/gpu.product: NVIDIA-A100-SXM4-80GB
|
||||
volumes:
|
||||
- name: devshm
|
||||
emptyDir:
|
||||
medium: Memory
|
||||
- label: "H100"
|
||||
agents:
|
||||
queue: H100
|
||||
plugins:
|
||||
- docker#v5.11.0:
|
||||
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
|
||||
command:
|
||||
- bash
|
||||
- .buildkite/nightly-benchmarks/run-benchmarks-suite.sh
|
||||
mount-buildkite-agent: true
|
||||
propagate-environment: true
|
||||
ipc: host
|
||||
gpus: all
|
||||
environment:
|
||||
- VLLM_USAGE_SOURCE
|
||||
- HF_TOKEN
|
||||
|
||||
@@ -0,0 +1,45 @@
|
||||
|
||||
# Nightly benchmark
|
||||
|
||||
The main goal of this benchmarking is two-fold:
|
||||
- Performance clarity: Provide clarity on which one (vllm, tensorrt-llm, lmdeploy and tgi) leads in performance in what workload.
|
||||
- Reproducible: one can run the exact same set of benchmarking commands inside the exact same docker by following reproducing instructions in [reproduce.md]().
|
||||
|
||||
|
||||
## Docker images
|
||||
|
||||
We benchmark vllm, tensorrt-llm, lmdeploy and tgi using the following docker images:
|
||||
- vllm/vllm-openai:v0.5.0.post1
|
||||
- nvcr.io/nvidia/tritonserver:24.04-trtllm-python-py3
|
||||
- openmmlab/lmdeploy:v0.5.0
|
||||
- ghcr.io/huggingface/text-generation-inference:2.1
|
||||
|
||||
<!-- Please check <a href="artifact://workspace/build/buildkite/vllm/performance-benchmark/.buildkite/nightly-benchmarks/nightly-pipeline.yaml">nightly-pipeline.yaml</a> artifact for more details on how we deploy the docker images. -->
|
||||
|
||||
|
||||
## Hardware
|
||||
|
||||
One AWS node with 8x NVIDIA A100 GPUs.
|
||||
|
||||
|
||||
## Workload description
|
||||
|
||||
We benchmark vllm, tensorrt-llm, lmdeploy and tgi using the following workload:
|
||||
|
||||
- Input length: randomly sample 500 prompts from ShareGPT dataset (with fixed random seed).
|
||||
- Output length: the corresponding output length of these 500 prompts.
|
||||
- Models: llama-3 8B, llama-3 70B, mixtral 8x7B.
|
||||
- Average QPS (query per second): 4 for the small model (llama-3 8B) and 2 for other two models. For each QPS, the arrival time of each query is determined using a random Poisson process (with fixed random seed).
|
||||
- Evaluation metrics: Throughput (higher the better), TTFT (time to the first token, lower the better), ITL (inter-token latency, lower the better).
|
||||
|
||||
<!-- Check <a href="artifact://workspace/build/buildkite/vllm/performance-benchmark/.buildkite/nightly-benchmarks/tests/nightly-tests.json">nightly-tests.json</a> artifact for more details. -->
|
||||
|
||||
## Plots
|
||||
|
||||
In the following plots, the dot shows the mean and the error bar shows the standard error of the mean. Value 0 means that the corresponding benchmark crashed.
|
||||
|
||||
<img src="artifact://nightly_results.png" alt="Benchmarking results" height=250 >
|
||||
|
||||
## Results
|
||||
|
||||
{nightly_results_benchmarking_table}
|
||||
@@ -0,0 +1,120 @@
|
||||
common_pod_spec: &common_pod_spec
|
||||
priorityClassName: perf-benchmark
|
||||
nodeSelector:
|
||||
nvidia.com/gpu.product: NVIDIA-A100-SXM4-80GB
|
||||
volumes:
|
||||
- name: devshm
|
||||
emptyDir:
|
||||
medium: Memory
|
||||
- name: hf-cache
|
||||
hostPath:
|
||||
path: /root/.cache/huggingface
|
||||
type: Directory
|
||||
|
||||
common_container_settings: &common_container_settings
|
||||
command:
|
||||
- bash .buildkite/nightly-benchmarks/run-nightly-suite.sh
|
||||
resources:
|
||||
limits:
|
||||
nvidia.com/gpu: 8
|
||||
volumeMounts:
|
||||
- name: devshm
|
||||
mountPath: /dev/shm
|
||||
- name: hf-cache
|
||||
mountPath: /root/.cache/huggingface
|
||||
env:
|
||||
- name: VLLM_USAGE_SOURCE
|
||||
value: ci-test
|
||||
- name: HF_HOME
|
||||
value: /root/.cache/huggingface
|
||||
- name: VLLM_SOURCE_CODE_LOC
|
||||
value: /workspace/build/buildkite/vllm/performance-benchmark
|
||||
- name: HF_TOKEN
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: hf-token-secret
|
||||
key: token
|
||||
|
||||
steps:
|
||||
- block: ":rocket: Ready for comparing vllm against alternatives? This will take 4 hours."
|
||||
- label: "A100 trt benchmark"
|
||||
priority: 100
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
<<: *common_pod_spec
|
||||
containers:
|
||||
- image: nvcr.io/nvidia/tritonserver:24.04-trtllm-python-py3
|
||||
<<: *common_container_settings
|
||||
|
||||
- label: "A100 lmdeploy benchmark"
|
||||
priority: 100
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
<<: *common_pod_spec
|
||||
containers:
|
||||
- image: openmmlab/lmdeploy:v0.5.0
|
||||
<<: *common_container_settings
|
||||
|
||||
|
||||
- label: "A100 vllm benchmark"
|
||||
priority: 100
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
<<: *common_pod_spec
|
||||
containers:
|
||||
- image: vllm/vllm-openai:latest
|
||||
<<: *common_container_settings
|
||||
|
||||
- label: "A100 tgi benchmark"
|
||||
priority: 100
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
<<: *common_pod_spec
|
||||
containers:
|
||||
- image: ghcr.io/huggingface/text-generation-inference:2.1
|
||||
<<: *common_container_settings
|
||||
|
||||
- wait
|
||||
|
||||
- label: "Plot"
|
||||
priority: 100
|
||||
agents:
|
||||
queue: A100
|
||||
plugins:
|
||||
- kubernetes:
|
||||
podSpec:
|
||||
<<: *common_pod_spec
|
||||
containers:
|
||||
- image: vllm/vllm-openai:v0.5.0.post1
|
||||
command:
|
||||
- bash .buildkite/nightly-benchmarks/scripts/nightly-annotate.sh
|
||||
resources:
|
||||
limits:
|
||||
nvidia.com/gpu: 8
|
||||
volumeMounts:
|
||||
- name: devshm
|
||||
mountPath: /dev/shm
|
||||
env:
|
||||
- name: VLLM_USAGE_SOURCE
|
||||
value: ci-test
|
||||
- name: VLLM_SOURCE_CODE_LOC
|
||||
value: /workspace/build/buildkite/vllm/performance-benchmark
|
||||
- name: HF_TOKEN
|
||||
valueFrom:
|
||||
secretKeyRef:
|
||||
name: hf-token-secret
|
||||
key: token
|
||||
|
||||
- wait
|
||||
@@ -0,0 +1,376 @@
|
||||
#!/bin/bash
|
||||
|
||||
# This script should be run inside the CI process
|
||||
# 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 -o pipefail
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
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
|
||||
}
|
||||
|
||||
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"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
# wait for vllm server to start
|
||||
# return 1 if vllm server crashes
|
||||
timeout 1200 bash -c '
|
||||
until curl -X POST localhost:8000/v1/completions; do
|
||||
sleep 1
|
||||
done' && return 0 || return 1
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
# kill all processes on GPU.
|
||||
pids=$(nvidia-smi --query-compute-apps=pid --format=csv,noheader)
|
||||
if [ -z "$pids" ]; then
|
||||
echo "No GPU processes found."
|
||||
else
|
||||
for pid in $pids; do
|
||||
kill -9 "$pid"
|
||||
echo "Killed process with PID: $pid"
|
||||
done
|
||||
|
||||
echo "All GPU processes have been killed."
|
||||
fi
|
||||
|
||||
# Sometimes kill with pid doesn't work properly, we can also kill all process running python or python3
|
||||
# since we are in container anyway
|
||||
pkill -9 -f python
|
||||
pkill -9 -f python3
|
||||
|
||||
# waiting for GPU processes to be fully killed
|
||||
# loop while nvidia-smi returns any processes
|
||||
while [ -n "$(nvidia-smi --query-compute-apps=pid --format=csv,noheader)" ]; do
|
||||
sleep 1
|
||||
echo "Waiting for GPU processes to be killed"
|
||||
done
|
||||
|
||||
# remove vllm config file
|
||||
rm -rf ~/.config/vllm
|
||||
|
||||
# Print the GPU memory usage
|
||||
# so that we know if all GPU processes are killed.
|
||||
gpu_memory_usage=$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i 0)
|
||||
# The memory usage should be 0 MB.
|
||||
echo "GPU 0 Memory Usage: $gpu_memory_usage MB"
|
||||
}
|
||||
|
||||
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/*"
|
||||
}
|
||||
|
||||
run_latency_tests() {
|
||||
# run latency tests using `benchmark_latency.py`
|
||||
# $1: a json file specifying latency test cases
|
||||
|
||||
local latency_test_file
|
||||
latency_test_file=$1
|
||||
|
||||
# Iterate over latency tests
|
||||
jq -c '.[]' "$latency_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 [[ ! "$test_name" =~ ^latency_ ]]; then
|
||||
echo "In latency-test.json, test_name must start with \"latency_\"."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# get arguments
|
||||
latency_params=$(echo "$params" | jq -r '.parameters')
|
||||
latency_args=$(json2args "$latency_params")
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
tp=$(echo "$latency_params" | jq -r '.tensor_parallel_size')
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $testname."
|
||||
continue
|
||||
fi
|
||||
|
||||
latency_command="python3 benchmark_latency.py \
|
||||
--output-json $RESULTS_FOLDER/${test_name}.json \
|
||||
$latency_args"
|
||||
|
||||
echo "Running test case $test_name"
|
||||
echo "Latency command: $latency_command"
|
||||
|
||||
# recoding benchmarking command ang GPU command
|
||||
jq_output=$(jq -n \
|
||||
--arg latency "$latency_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
'{
|
||||
latency_command: $latency,
|
||||
gpu_type: $gpu
|
||||
}')
|
||||
echo "$jq_output" > "$RESULTS_FOLDER/$test_name.commands"
|
||||
|
||||
# run the benchmark
|
||||
eval "$latency_command"
|
||||
|
||||
kill_gpu_processes
|
||||
|
||||
done
|
||||
}
|
||||
|
||||
|
||||
run_throughput_tests() {
|
||||
# run throughput tests using `benchmark_throughput.py`
|
||||
# $1: a json file specifying throughput test cases
|
||||
|
||||
local throughput_test_file
|
||||
throughput_test_file=$1
|
||||
|
||||
# Iterate over throughput tests
|
||||
jq -c '.[]' "$throughput_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 [[ ! "$test_name" =~ ^throughput_ ]]; then
|
||||
echo "In throughput-test.json, test_name must start with \"throughput_\"."
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# if TEST_SELECTOR is set, only run the test cases that match the selector
|
||||
if [[ -n "$TEST_SELECTOR" ]] && [[ ! "$test_name" =~ $TEST_SELECTOR ]]; then
|
||||
echo "Skip test case $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# get arguments
|
||||
throughput_params=$(echo "$params" | jq -r '.parameters')
|
||||
throughput_args=$(json2args "$throughput_params")
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
tp=$(echo $throughput_params | jq -r '.tensor_parallel_size')
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $testname."
|
||||
continue
|
||||
fi
|
||||
|
||||
throughput_command="python3 benchmark_throughput.py \
|
||||
--output-json $RESULTS_FOLDER/${test_name}.json \
|
||||
$throughput_args"
|
||||
|
||||
echo "Running test case $test_name"
|
||||
echo "Throughput command: $throughput_command"
|
||||
# recoding benchmarking command ang GPU command
|
||||
jq_output=$(jq -n \
|
||||
--arg command "$throughput_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
'{
|
||||
throughput_command: $command,
|
||||
gpu_type: $gpu
|
||||
}')
|
||||
echo "$jq_output" > "$RESULTS_FOLDER/$test_name.commands"
|
||||
|
||||
# run the benchmark
|
||||
eval "$throughput_command"
|
||||
|
||||
kill_gpu_processes
|
||||
|
||||
done
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `benchmark_serving.py`
|
||||
# $1: a json file specifying serving test cases
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# Iterate over serving tests
|
||||
jq -c '.[]' "$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 $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
|
||||
# get client and server arguments
|
||||
server_params=$(echo "$params" | jq -r '.server_parameters')
|
||||
client_params=$(echo "$params" | jq -r '.client_parameters')
|
||||
server_args=$(json2args "$server_params")
|
||||
client_args=$(json2args "$client_params")
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
tp=$(echo "$server_params" | jq -r '.tensor_parallel_size')
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $testname."
|
||||
continue
|
||||
fi
|
||||
|
||||
# check if server model and client model is aligned
|
||||
server_model=$(echo "$server_params" | jq -r '.model')
|
||||
client_model=$(echo "$client_params" | jq -r '.model')
|
||||
if [[ $server_model != "$client_model" ]]; then
|
||||
echo "Server model and client model must be the same. Skip testcase $testname."
|
||||
continue
|
||||
fi
|
||||
|
||||
server_command="python3 \
|
||||
-m vllm.entrypoints.openai.api_server \
|
||||
$server_args"
|
||||
|
||||
# run the server
|
||||
echo "Running test case $test_name"
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
server_pid=$!
|
||||
|
||||
# wait until the server is alive
|
||||
wait_for_server
|
||||
if [ $? -eq 0 ]; then
|
||||
echo ""
|
||||
echo "vllm server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "vllm failed to start within the timeout period."
|
||||
fi
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
echo "qps was $qps"
|
||||
qps="inf"
|
||||
echo "now qps is $qps"
|
||||
fi
|
||||
|
||||
new_test_name=$test_name"_qps_"$qps
|
||||
|
||||
client_command="python3 benchmark_serving.py \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
$client_args"
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
eval "$client_command"
|
||||
|
||||
# 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
|
||||
|
||||
# clean up
|
||||
kill -9 $server_pid
|
||||
kill_gpu_processes
|
||||
done
|
||||
}
|
||||
|
||||
main() {
|
||||
check_gpus
|
||||
check_hf_token
|
||||
|
||||
# dependencies
|
||||
(which wget && which curl) || (apt-get update && apt-get install -y wget curl)
|
||||
(which jq) || (apt-get update && apt-get -y install jq)
|
||||
|
||||
# get the current IP address, required by benchmark_serving.py
|
||||
export VLLM_HOST_IP=$(hostname -I | awk '{print $1}')
|
||||
# turn of the reporting of the status of each request, to clean up the terminal output
|
||||
export VLLM_LOG_LEVEL="WARNING"
|
||||
|
||||
# prepare for benchmarking
|
||||
cd benchmarks || exit 1
|
||||
wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
QUICK_BENCHMARK_ROOT=../.buildkite/nightly-benchmarks/
|
||||
|
||||
# benchmarking
|
||||
run_serving_tests $QUICK_BENCHMARK_ROOT/tests/serving-tests.json
|
||||
run_latency_tests $QUICK_BENCHMARK_ROOT/tests/latency-tests.json
|
||||
run_throughput_tests $QUICK_BENCHMARK_ROOT/tests/throughput-tests.json
|
||||
|
||||
|
||||
# postprocess benchmarking results
|
||||
pip install tabulate pandas
|
||||
python3 $QUICK_BENCHMARK_ROOT/scripts/convert-results-json-to-markdown.py
|
||||
|
||||
upload_to_buildkite
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@@ -0,0 +1,76 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -o pipefail
|
||||
set -x
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
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
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
check_gpus
|
||||
check_hf_token
|
||||
|
||||
df -h
|
||||
|
||||
(which wget && which curl) || (apt-get update && apt-get install -y wget curl)
|
||||
(which jq) || (apt-get update && apt-get -y install jq)
|
||||
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
|
||||
|
||||
|
||||
# run lmdeploy
|
||||
if which lmdeploy >/dev/null; then
|
||||
echo "lmdeploy is available, redirect to run-lmdeploy-nightly.sh"
|
||||
bash ../.buildkite/nightly-benchmarks/scripts/run-lmdeploy-nightly.sh
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# run tgi
|
||||
if [ -e /tgi-entrypoint.sh ]; then
|
||||
echo "tgi is available, redirect to run-tgi-nightly.sh"
|
||||
bash ../.buildkite/nightly-benchmarks/scripts/run-tgi-nightly.sh
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# run trt
|
||||
if which trtllm-build >/dev/null; then
|
||||
echo "trtllm is available, redirect to run-trt-nightly.sh"
|
||||
bash ../.buildkite/nightly-benchmarks/scripts/run-trt-nightly.sh
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# run vllm
|
||||
if [ -e /vllm-workspace ]; then
|
||||
echo "vllm is available, redirect to run-vllm-nightly.sh"
|
||||
bash ../.buildkite/nightly-benchmarks/scripts/run-vllm-nightly.sh
|
||||
exit 0
|
||||
fi
|
||||
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@@ -0,0 +1,192 @@
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
import pandas as pd
|
||||
from tabulate import tabulate
|
||||
|
||||
results_folder = Path("results/")
|
||||
|
||||
# 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",
|
||||
"gpu_type": "GPU",
|
||||
# "completed": "# of req.",
|
||||
"request_throughput": "Tput (req/s)",
|
||||
# "input_throughput": "Input Tput (tok/s)",
|
||||
# "output_throughput": "Output Tput (tok/s)",
|
||||
"mean_ttft_ms": "Mean TTFT (ms)",
|
||||
"median_ttft_ms": "Median TTFT (ms)",
|
||||
"p99_ttft_ms": "P99 TTFT (ms)",
|
||||
# "mean_tpot_ms": "Mean TPOT (ms)",
|
||||
# "median_tpot_ms": "Median",
|
||||
# "p99_tpot_ms": "P99",
|
||||
"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, "r") 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()
|
||||
})
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
# collect results
|
||||
for test_file in results_folder.glob("*.json"):
|
||||
|
||||
with open(test_file, "r") as f:
|
||||
raw_result = json.loads(f.read())
|
||||
|
||||
if "serving" in str(test_file):
|
||||
# this result is generated via `benchmark_serving.py`
|
||||
|
||||
# attach the benchmarking command to raw_result
|
||||
with open(test_file.with_suffix(".commands"), "r") as f:
|
||||
command = json.loads(f.read())
|
||||
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 `benchmark_latency.py`
|
||||
|
||||
# attach the benchmarking command to raw_result
|
||||
with open(test_file.with_suffix(".commands"), "r") as f:
|
||||
command = json.loads(f.read())
|
||||
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 `benchmark_throughput.py`
|
||||
|
||||
# attach the benchmarking command to raw_result
|
||||
with open(test_file.with_suffix(".commands"), "r") as f:
|
||||
command = json.loads(f.read())
|
||||
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)
|
||||
|
||||
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:
|
||||
serving_results = serving_results[list(
|
||||
serving_column_mapping.keys())].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)
|
||||
|
||||
# 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)
|
||||
|
||||
# document the result
|
||||
with open(results_folder / "benchmark_results.md", "w") as f:
|
||||
|
||||
results = read_markdown(
|
||||
"../.buildkite/nightly-benchmarks/tests/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,
|
||||
benchmarking_results_in_json_string=processed_results_json)
|
||||
f.write(results)
|
||||
|
||||
# document benchmarking results in json
|
||||
with open(results_folder / "benchmark_results.json", "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))
|
||||
@@ -0,0 +1,26 @@
|
||||
import argparse
|
||||
|
||||
from transformers import AutoTokenizer
|
||||
|
||||
|
||||
def main(model, cachedir):
|
||||
# Load the tokenizer and save it to the specified directory
|
||||
tokenizer = AutoTokenizer.from_pretrained(model)
|
||||
tokenizer.save_pretrained(cachedir)
|
||||
print(f"Tokenizer saved to {cachedir}")
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Download and save Hugging Face tokenizer")
|
||||
parser.add_argument("--model",
|
||||
type=str,
|
||||
required=True,
|
||||
help="Name of the model")
|
||||
parser.add_argument("--cachedir",
|
||||
type=str,
|
||||
required=True,
|
||||
help="Directory to save the tokenizer")
|
||||
|
||||
args = parser.parse_args()
|
||||
main(args.model, args.cachedir)
|
||||
@@ -0,0 +1,6 @@
|
||||
from lmdeploy.serve.openai.api_client import APIClient
|
||||
|
||||
api_client = APIClient("http://localhost:8000")
|
||||
model_name = api_client.available_models[0]
|
||||
|
||||
print(model_name)
|
||||
@@ -0,0 +1,102 @@
|
||||
#!/bin/bash
|
||||
|
||||
|
||||
server_params=$1
|
||||
common_params=$2
|
||||
|
||||
|
||||
|
||||
model_path=$(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_output_len=$(echo "$server_params" | jq -r '.max_output_len')
|
||||
trt_llm_version=$(echo "$server_params" | jq -r '.trt_llm_version')
|
||||
|
||||
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}/${model_name}-trt-engine
|
||||
|
||||
cd ~
|
||||
rm -rf tensorrt-demo
|
||||
git clone https://github.com/neuralmagic/tensorrt-demo.git
|
||||
cd tensorrt-demo
|
||||
tensorrt_demo_dir=$(pwd)
|
||||
|
||||
# make sure the parameter inside tensorrt_demo is consistent to envvar
|
||||
sed -i.bak "/key: \"tokenizer_dir\"/,/string_value:/s|string_value: \".*\"|string_value: \"$model_path\"|" ./triton_model_repo/postprocessing/config.pbtxt
|
||||
sed -i.bak "/key: \"tokenizer_dir\"/,/string_value:/s|string_value: \".*\"|string_value: \"$model_path\"|" ./triton_model_repo/preprocessing/config.pbtxt
|
||||
sed -i.bak "s|\(max_batch_size:\s*\)[0-9]*|\1$max_batch_size|g" ./triton_model_repo/ensemble/config.pbtxt
|
||||
sed -i.bak "s|\(max_batch_size:\s*\)[0-9]*|\1$max_batch_size|g" ./triton_model_repo/preprocessing/config.pbtxt
|
||||
sed -i.bak "s|\(max_batch_size:\s*\)[0-9]*|\1$max_batch_size|g" ./triton_model_repo/postprocessing/config.pbtxt
|
||||
sed -i.bak "s|\(max_batch_size:\s*\)[0-9]*|\1$max_batch_size|g" ./triton_model_repo/tensorrt_llm_bls/config.pbtxt
|
||||
|
||||
|
||||
cd /
|
||||
rm -rf tensorrtllm_backend
|
||||
git clone https://github.com/triton-inference-server/tensorrtllm_backend.git
|
||||
git lfs install
|
||||
cd tensorrtllm_backend
|
||||
git checkout $trt_llm_version
|
||||
tensorrtllm_backend_dir=$(pwd)
|
||||
git submodule update --init --recursive
|
||||
cp -r ${tensorrt_demo_dir}/triton_model_repo ${tensorrtllm_backend_dir}/
|
||||
|
||||
cd /tensorrtllm_backend
|
||||
cd ./tensorrt_llm/examples/${model_type}
|
||||
|
||||
|
||||
if echo "$common_params" | jq -e 'has("fp8")' > /dev/null; then
|
||||
|
||||
echo "Key 'fp8' exists in common params. Use quantize.py instead of convert_checkpoint.py"
|
||||
echo "Reference: https://github.com/NVIDIA/TensorRT-LLM/blob/main/examples/llama/README.md"
|
||||
python ../quantization/quantize.py \
|
||||
--model_dir ${model_path} \
|
||||
--dtype ${model_dtype} \
|
||||
--tp_size ${model_tp_size} \
|
||||
--output_dir ${trt_model_path} \
|
||||
--qformat fp8 \
|
||||
--kv_cache_dtype fp8 \
|
||||
--calib_size 2
|
||||
|
||||
else
|
||||
|
||||
echo "Key 'fp8' does not exist in common params. Use convert_checkpoint.py"
|
||||
python3 convert_checkpoint.py \
|
||||
--model_dir ${model_path} \
|
||||
--dtype ${model_dtype} \
|
||||
--tp_size ${model_tp_size} \
|
||||
--output_dir ${trt_model_path}
|
||||
|
||||
fi
|
||||
|
||||
|
||||
|
||||
trtllm-build \
|
||||
--checkpoint_dir=${trt_model_path} \
|
||||
--gpt_attention_plugin=${model_dtype} \
|
||||
--gemm_plugin=${model_dtype} \
|
||||
--remove_input_padding=enable \
|
||||
--paged_kv_cache=enable \
|
||||
--tp_size=${model_tp_size} \
|
||||
--max_batch_size=${max_batch_size} \
|
||||
--max_input_len=${max_input_len} \
|
||||
--max_output_len=${max_output_len} \
|
||||
--max_num_tokens=${max_output_len} \
|
||||
--opt_num_tokens=${max_output_len} \
|
||||
--output_dir=${trt_engine_path}
|
||||
|
||||
cd /tensorrtllm_backend/triton_model_repo
|
||||
rm -rf ./tensorrt_llm/1/*
|
||||
cp -r ${trt_engine_path}/* ./tensorrt_llm/1
|
||||
cd /tensorrtllm_backend
|
||||
python3 scripts/launch_triton_server.py \
|
||||
--world_size=${model_tp_size} \
|
||||
--model_repo=/tensorrtllm_backend/triton_model_repo &
|
||||
@@ -0,0 +1,40 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -ex
|
||||
set -o pipefail
|
||||
|
||||
|
||||
main() {
|
||||
|
||||
(which wget && which curl) || (apt-get update && apt-get install -y wget curl)
|
||||
(which jq) || (apt-get update && apt-get -y install jq)
|
||||
|
||||
if [ ! -f /workspace/buildkite-agent ]; then
|
||||
echo "buildkite-agent binary not found. Skip plotting the results."
|
||||
exit 0
|
||||
fi
|
||||
|
||||
# initial annotation
|
||||
description="$VLLM_SOURCE_CODE_LOC/.buildkite/nightly-benchmarks/nightly-descriptions.md"
|
||||
|
||||
# download results
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
mkdir -p results/
|
||||
/workspace/buildkite-agent artifact download 'results/*nightly_results.json' results/
|
||||
ls
|
||||
ls results/
|
||||
|
||||
# generate figures
|
||||
python3 -m pip install tabulate pandas matplotlib
|
||||
python3 $VLLM_SOURCE_CODE_LOC/.buildkite/nightly-benchmarks/scripts/plot-nightly-results.py \
|
||||
--description $description \
|
||||
--results-folder results/
|
||||
|
||||
# upload results and figures
|
||||
/workspace/buildkite-agent artifact upload "nightly_results.png"
|
||||
/workspace/buildkite-agent artifact upload $VLLM_SOURCE_CODE_LOC/.buildkite/nightly-benchmarks/nightly-pipeline.yaml
|
||||
/workspace/buildkite-agent artifact upload $VLLM_SOURCE_CODE_LOC/.buildkite/nightly-benchmarks/tests/nightly-tests.json
|
||||
/workspace/buildkite-agent annotate --style "success" --context "nightly-benchmarks-results" --append < nightly_results.md
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@@ -0,0 +1,135 @@
|
||||
import argparse
|
||||
import json
|
||||
import math
|
||||
from pathlib import Path
|
||||
|
||||
import matplotlib.pyplot as plt
|
||||
import pandas as pd
|
||||
from tabulate import tabulate
|
||||
|
||||
|
||||
def parse_arguments():
|
||||
parser = argparse.ArgumentParser(
|
||||
description=
|
||||
'Parse command line arguments for summary-nightly-results script.')
|
||||
parser.add_argument('--results-folder',
|
||||
type=str,
|
||||
required=True,
|
||||
help='The folder where the results are stored.')
|
||||
parser.add_argument('--description',
|
||||
type=str,
|
||||
required=True,
|
||||
help='Description of the results.')
|
||||
|
||||
args = parser.parse_args()
|
||||
return args
|
||||
|
||||
|
||||
def main(args):
|
||||
bar_colors = ['#56B4E9', '#009E73', '#D55E00', '#E69F00']
|
||||
results_folder = Path(args.results_folder)
|
||||
|
||||
results = []
|
||||
|
||||
# collect results
|
||||
for test_file in results_folder.glob("*_nightly_results.json"):
|
||||
with open(test_file, "r") as f:
|
||||
results = results + json.loads(f.read())
|
||||
|
||||
# generate markdown table
|
||||
df = pd.DataFrame.from_dict(results)
|
||||
|
||||
md_table = tabulate(df, headers='keys', tablefmt='pipe', showindex=False)
|
||||
|
||||
with open(args.description, "r") as f:
|
||||
description = f.read()
|
||||
|
||||
description = description.format(
|
||||
nightly_results_benchmarking_table=md_table)
|
||||
|
||||
with open("nightly_results.md", "w") as f:
|
||||
f.write(description)
|
||||
|
||||
plt.rcParams.update({'font.size': 20})
|
||||
|
||||
# plot results
|
||||
fig, axes = plt.subplots(3, 3, figsize=(16, 14))
|
||||
fig.subplots_adjust(hspace=1)
|
||||
methods = ["vllm", "trt", "lmdeploy", "tgi"]
|
||||
for i, model in enumerate(["llama8B", "llama70B", "mixtral8x7B"]):
|
||||
for j, metric in enumerate(["TTFT", "ITL"]):
|
||||
means, stds = [], []
|
||||
for method in methods:
|
||||
target = df['Test name'].str.contains(model)
|
||||
target = target & df['Engine'].str.contains(method)
|
||||
filtered_df = df[target]
|
||||
|
||||
if filtered_df.empty:
|
||||
means.append(0.)
|
||||
stds.append(0.)
|
||||
else:
|
||||
means.append(filtered_df[f"Mean {metric} (ms)"].values[0])
|
||||
std = filtered_df[f"Std {metric} (ms)"].values[0]
|
||||
success = filtered_df["Successful req."].values[0]
|
||||
stds.append(std / math.sqrt(success))
|
||||
|
||||
print(model, metric)
|
||||
print(means, stds)
|
||||
|
||||
ax = axes[i, j + 1]
|
||||
|
||||
bars = ax.bar(
|
||||
["vllm", "trt", "lmdeploy", "tgi"],
|
||||
means,
|
||||
yerr=stds,
|
||||
capsize=10,
|
||||
)
|
||||
for idx, bar in enumerate(bars):
|
||||
bar.set_color(bar_colors[idx])
|
||||
ax.set_ylim(bottom=0)
|
||||
|
||||
ax.set_ylabel(f"{metric} (ms)")
|
||||
ax.set_title(f"{model} {metric}")
|
||||
ax.grid(axis='y')
|
||||
|
||||
metric = "Tput"
|
||||
j = 0
|
||||
if True:
|
||||
tputs = []
|
||||
for method in methods:
|
||||
target = df['Test name'].str.contains(model)
|
||||
target = target & df['Engine'].str.contains(method)
|
||||
filtered_df = df[target]
|
||||
|
||||
if filtered_df.empty:
|
||||
tputs.append(0.)
|
||||
else:
|
||||
input_tput = filtered_df["Input Tput (tok/s)"].values[0]
|
||||
output_tput = filtered_df["Output Tput (tok/s)"].values[0]
|
||||
tputs.append(input_tput + output_tput)
|
||||
|
||||
print(model, metric)
|
||||
print(tputs)
|
||||
|
||||
ax = axes[i, j]
|
||||
|
||||
bars = ax.bar(
|
||||
["vllm", "trt", "lmdeploy", "tgi"],
|
||||
tputs,
|
||||
)
|
||||
for idx, bar in enumerate(bars):
|
||||
bar.set_color(bar_colors[idx])
|
||||
|
||||
ax.set_ylim(bottom=0)
|
||||
|
||||
ax.set_ylabel("Tput (token/s)")
|
||||
ax.set_title(f"{model} {metric}")
|
||||
ax.grid(axis='y')
|
||||
|
||||
fig.tight_layout()
|
||||
fig.savefig("nightly_results.png", bbox_inches='tight', dpi=400)
|
||||
|
||||
|
||||
if __name__ == '__main__':
|
||||
args = parse_arguments()
|
||||
main(args)
|
||||
@@ -0,0 +1,218 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -o pipefail
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
pkill lmdeploy || true
|
||||
# waiting for GPU processes to be fully killed
|
||||
sleep 10
|
||||
# Print the GPU memory usage
|
||||
# so that we know if all GPU processes are killed.
|
||||
gpu_memory_usage=$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i 0)
|
||||
# The memory usage should be 0 MB.
|
||||
echo "GPU 0 Memory Usage: $gpu_memory_usage MB"
|
||||
}
|
||||
|
||||
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"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
# wait for vllm server to start
|
||||
# return 1 if vllm server crashes
|
||||
timeout 1200 bash -c '
|
||||
until curl -s localhost:8000/v1/completions > /dev/null; do
|
||||
sleep 1
|
||||
done' && return 0 || return 1
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `benchmark_serving.py`
|
||||
# $1: a json file specifying serving test cases
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# Iterate over serving tests
|
||||
jq -c '.[]' "$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_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 $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# append lmdeploy to the test name
|
||||
test_name=lmdeploy_$test_name
|
||||
|
||||
# get common parameters
|
||||
common_params=$(echo "$params" | jq -r '.common_parameters')
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
dataset_name=$(echo "$common_params" | jq -r '.dataset_name')
|
||||
dataset_path=$(echo "$common_params" | jq -r '.dataset_path')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
num_prompts=$(echo "$common_params" | jq -r '.num_prompts')
|
||||
|
||||
|
||||
|
||||
# get client and server arguments
|
||||
server_params=$(echo "$params" | jq -r '.lmdeploy_server_parameters')
|
||||
client_params=$(echo "$params" | jq -r '.lmdeploy_client_parameters')
|
||||
server_args=$(json2args "$server_params")
|
||||
client_args=$(json2args "$client_params")
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# prepare tokenizer
|
||||
rm -rf /tokenizer_cache
|
||||
mkdir /tokenizer_cache
|
||||
python ../.buildkite/nightly-benchmarks/scripts/download-tokenizer.py \
|
||||
--model "$model" \
|
||||
--cachedir /tokenizer_cache
|
||||
|
||||
server_command="lmdeploy serve api_server $model \
|
||||
--tp $tp \
|
||||
--server-port $port \
|
||||
$server_args"
|
||||
|
||||
# run the server
|
||||
echo "Running test case $test_name"
|
||||
echo "Server command: $server_command"
|
||||
bash -c "$server_command" &
|
||||
|
||||
# wait until the server is alive
|
||||
wait_for_server
|
||||
if [ $? -eq 0 ]; then
|
||||
echo ""
|
||||
echo "lmdeploy server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "lmdeploy failed to start within the timeout period."
|
||||
break
|
||||
fi
|
||||
|
||||
# get model name
|
||||
model_name=$(python ../.buildkite/nightly-benchmarks/scripts/get-lmdeploy-modelname.py)
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
echo "qps was $qps"
|
||||
qps="inf"
|
||||
echo "now qps is $qps"
|
||||
fi
|
||||
|
||||
new_test_name=$test_name"_qps_"$qps
|
||||
|
||||
client_command="python3 benchmark_serving.py \
|
||||
--backend lmdeploy \
|
||||
--tokenizer /tokenizer_cache \
|
||||
--dataset-name $dataset_name \
|
||||
--dataset-path $dataset_path \
|
||||
--num-prompts $num_prompts \
|
||||
--port $port \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
--model \"$model_name\" \
|
||||
$client_args"
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
eval "$client_command"
|
||||
|
||||
# record the benchmarking commands
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
--arg engine "lmdeploy" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu,
|
||||
engine: $engine
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
done
|
||||
|
||||
# clean up
|
||||
kill_gpu_processes
|
||||
rm -rf /root/.cache/huggingface/*
|
||||
done
|
||||
}
|
||||
|
||||
|
||||
upload_to_buildkite() {
|
||||
# upload the benchmarking results to buildkite
|
||||
|
||||
# if the agent binary is not found, skip uploading the results, exit 0
|
||||
if [ ! -f /workspace/buildkite-agent ]; then
|
||||
echo "buildkite-agent binary not found. Skip uploading the results."
|
||||
return 0
|
||||
fi
|
||||
# /workspace/buildkite-agent annotate --style "success" --context "benchmark-results" --append < $RESULTS_FOLDER/${CURRENT_LLM_SERVING_ENGINE}_nightly_results.md
|
||||
/workspace/buildkite-agent artifact upload "$RESULTS_FOLDER/*"
|
||||
}
|
||||
|
||||
|
||||
main() {
|
||||
|
||||
check_gpus
|
||||
# enter vllm directory
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
BENCHMARK_ROOT=../.buildkite/nightly-benchmarks/
|
||||
|
||||
python -m pip install transformers==4.41.2
|
||||
|
||||
export CURRENT_LLM_SERVING_ENGINE=lmdeploy
|
||||
run_serving_tests $BENCHMARK_ROOT/tests/nightly-tests.json
|
||||
python -m pip install tabulate pandas
|
||||
python $BENCHMARK_ROOT/scripts/summary-nightly-results.py
|
||||
upload_to_buildkite
|
||||
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@@ -0,0 +1,216 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -o pipefail
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
pkill text-generation || true
|
||||
# waiting for GPU processes to be fully killed
|
||||
sleep 10
|
||||
# Print the GPU memory usage
|
||||
# so that we know if all GPU processes are killed.
|
||||
gpu_memory_usage=$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i 0)
|
||||
# The memory usage should be 0 MB.
|
||||
echo "GPU 0 Memory Usage: $gpu_memory_usage MB"
|
||||
}
|
||||
|
||||
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"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
timeout 1200 bash -c '
|
||||
until curl -s localhost:8000/generate_stream > /dev/null; do
|
||||
sleep 1
|
||||
done' && return 0 || return 1
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `benchmark_serving.py`
|
||||
# $1: a json file specifying serving test cases
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# Iterate over serving tests
|
||||
jq -c '.[]' "$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_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 $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# append tgi to the test name
|
||||
test_name=tgi_$test_name
|
||||
|
||||
# get common parameters
|
||||
common_params=$(echo "$params" | jq -r '.common_parameters')
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
dataset_name=$(echo "$common_params" | jq -r '.dataset_name')
|
||||
dataset_path=$(echo "$common_params" | jq -r '.dataset_path')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
num_prompts=$(echo "$common_params" | jq -r '.num_prompts')
|
||||
|
||||
# get client and server arguments
|
||||
server_params=$(echo "$params" | jq -r '.tgi_server_parameters')
|
||||
client_params=$(echo "$params" | jq -r '.tgi_client_parameters')
|
||||
server_args=$(json2args "$server_params")
|
||||
client_args=$(json2args "$client_params")
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required num-shard $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
if echo "$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
|
||||
|
||||
|
||||
|
||||
|
||||
# run the server
|
||||
echo "Running test case $test_name"
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
|
||||
# wait until the server is alive
|
||||
wait_for_server
|
||||
if [ $? -eq 0 ]; then
|
||||
echo ""
|
||||
echo "tgi server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "tgi failed to start within the timeout period."
|
||||
break
|
||||
fi
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
echo "qps was $qps"
|
||||
qps="inf"
|
||||
echo "now qps is $qps"
|
||||
fi
|
||||
|
||||
new_test_name=$test_name"_qps_"$qps
|
||||
|
||||
client_command="python3 benchmark_serving.py \
|
||||
--backend tgi \
|
||||
--model $model \
|
||||
--dataset-name $dataset_name \
|
||||
--dataset-path $dataset_path \
|
||||
--num-prompts $num_prompts \
|
||||
--port $port \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
$client_args"
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
eval "$client_command"
|
||||
|
||||
# record the benchmarking commands
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
--arg engine "tgi" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu,
|
||||
engine: $engine
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
done
|
||||
|
||||
# clean up
|
||||
kill_gpu_processes
|
||||
rm -rf /root/.cache/huggingface/*
|
||||
done
|
||||
}
|
||||
|
||||
|
||||
|
||||
upload_to_buildkite() {
|
||||
# upload the benchmarking results to buildkite
|
||||
|
||||
# if the agent binary is not found, skip uploading the results, exit 0
|
||||
if [ ! -f /workspace/buildkite-agent ]; then
|
||||
echo "buildkite-agent binary not found. Skip uploading the results."
|
||||
return 0
|
||||
fi
|
||||
# /workspace/buildkite-agent annotate --style "success" --context "benchmark-results" --append < $RESULTS_FOLDER/${CURRENT_LLM_SERVING_ENGINE}_nightly_results.md
|
||||
/workspace/buildkite-agent artifact upload "$RESULTS_FOLDER/*"
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
check_gpus
|
||||
# enter vllm directory
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
BENCHMARK_ROOT=../.buildkite/nightly-benchmarks/
|
||||
|
||||
export CURRENT_LLM_SERVING_ENGINE=tgi
|
||||
run_serving_tests $BENCHMARK_ROOT/tests/nightly-tests.json
|
||||
python -m pip install tabulate pandas
|
||||
python $BENCHMARK_ROOT/scripts/summary-nightly-results.py
|
||||
upload_to_buildkite
|
||||
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@@ -0,0 +1,214 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -o pipefail
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
pkill tritonserver || true
|
||||
# waiting for GPU processes to be fully killed
|
||||
sleep 20
|
||||
# Print the GPU memory usage
|
||||
# so that we know if all GPU processes are killed.
|
||||
gpu_memory_usage=$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i 0)
|
||||
# The memory usage should be 0 MB.
|
||||
echo "GPU 0 Memory Usage: $gpu_memory_usage MB"
|
||||
}
|
||||
|
||||
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"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
timeout 1200 bash -c '
|
||||
until curl -s localhost:8000/generate_stream > /dev/null; do
|
||||
sleep 1
|
||||
done' && return 0 || return 1
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `benchmark_serving.py`
|
||||
# $1: a json file specifying serving test cases
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# Iterate over serving tests
|
||||
jq -c '.[]' "$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_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 $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# append trt to the test name
|
||||
test_name=trt_$test_name
|
||||
|
||||
# get common parameters
|
||||
common_params=$(echo "$params" | jq -r '.common_parameters')
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
dataset_name=$(echo "$common_params" | jq -r '.dataset_name')
|
||||
dataset_path=$(echo "$common_params" | jq -r '.dataset_path')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
num_prompts=$(echo "$common_params" | jq -r '.num_prompts')
|
||||
|
||||
# get client and server arguments
|
||||
server_params=$(echo "$params" | jq -r '.trt_server_parameters')
|
||||
client_params=$(echo "$params" | jq -r '.trt_client_parameters')
|
||||
client_args=$(json2args "$client_params")
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required model_tp_size $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
|
||||
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
|
||||
|
||||
echo "Running test case $test_name"
|
||||
bash ../.buildkite/nightly-benchmarks/scripts/launch-trt-server.sh "$server_params" "$common_params"
|
||||
|
||||
# wait until the server is alive
|
||||
wait_for_server
|
||||
if [ $? -eq 0 ]; then
|
||||
echo ""
|
||||
echo "trt server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "trt failed to start within the timeout period."
|
||||
break
|
||||
fi
|
||||
|
||||
# prepare tokenizer
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
rm -rf /tokenizer_cache
|
||||
mkdir /tokenizer_cache
|
||||
python ../.buildkite/nightly-benchmarks/scripts/download-tokenizer.py \
|
||||
--model "$model" \
|
||||
--cachedir /tokenizer_cache
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
echo "qps was $qps"
|
||||
qps="inf"
|
||||
echo "now qps is $qps"
|
||||
fi
|
||||
|
||||
new_test_name=$test_name"_qps_"$qps
|
||||
|
||||
client_command="python3 benchmark_serving.py \
|
||||
--backend tensorrt-llm \
|
||||
--tokenizer /tokenizer_cache \
|
||||
--model $model \
|
||||
--dataset-name $dataset_name \
|
||||
--dataset-path $dataset_path \
|
||||
--num-prompts $num_prompts \
|
||||
--port $port \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
$client_args"
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
eval "$client_command"
|
||||
|
||||
server_command=""
|
||||
# record the benchmarking commands
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
--arg engine "trt" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu,
|
||||
engine: $engine
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
done
|
||||
|
||||
# clean up
|
||||
kill_gpu_processes
|
||||
rm -rf /root/.cache/huggingface/*
|
||||
done
|
||||
}
|
||||
|
||||
upload_to_buildkite() {
|
||||
# upload the benchmarking results to buildkite
|
||||
|
||||
# if the agent binary is not found, skip uploading the results, exit 0
|
||||
if [ ! -f /workspace/buildkite-agent ]; then
|
||||
echo "buildkite-agent binary not found. Skip uploading the results."
|
||||
return 0
|
||||
fi
|
||||
# /workspace/buildkite-agent annotate --style "success" --context "benchmark-results" --append < $RESULTS_FOLDER/${CURRENT_LLM_SERVING_ENGINE}_nightly_results.md
|
||||
/workspace/buildkite-agent artifact upload "$RESULTS_FOLDER/*"
|
||||
}
|
||||
|
||||
|
||||
main() {
|
||||
|
||||
check_gpus
|
||||
|
||||
|
||||
# enter vllm directory
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
BENCHMARK_ROOT=../.buildkite/nightly-benchmarks/
|
||||
|
||||
# update transformers package, to make sure mixtral tokenizer is available
|
||||
python -m pip install transformers -U
|
||||
|
||||
export CURRENT_LLM_SERVING_ENGINE=trt
|
||||
run_serving_tests $BENCHMARK_ROOT/tests/nightly-tests.json
|
||||
python -m pip install tabulate pandas
|
||||
python $BENCHMARK_ROOT/scripts/summary-nightly-results.py
|
||||
upload_to_buildkite
|
||||
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@@ -0,0 +1,221 @@
|
||||
#!/bin/bash
|
||||
|
||||
set -o pipefail
|
||||
|
||||
check_gpus() {
|
||||
# check the number of GPUs and GPU type.
|
||||
declare -g gpu_count=$(nvidia-smi --list-gpus | wc -l)
|
||||
if [[ $gpu_count -gt 0 ]]; then
|
||||
echo "GPU found."
|
||||
else
|
||||
echo "Need at least 1 GPU to run benchmarking."
|
||||
exit 1
|
||||
fi
|
||||
declare -g gpu_type=$(echo $(nvidia-smi --query-gpu=name --format=csv,noheader) | awk '{print $2}')
|
||||
echo "GPU type is $gpu_type"
|
||||
}
|
||||
|
||||
kill_gpu_processes() {
|
||||
# kill all processes on GPU.
|
||||
pkill pt_main_thread
|
||||
sleep 10
|
||||
|
||||
# remove vllm config file
|
||||
rm -rf ~/.config/vllm
|
||||
|
||||
# Print the GPU memory usage
|
||||
# so that we know if all GPU processes are killed.
|
||||
gpu_memory_usage=$(nvidia-smi --query-gpu=memory.used --format=csv,noheader,nounits -i 0)
|
||||
# The memory usage should be 0 MB.
|
||||
echo "GPU 0 Memory Usage: $gpu_memory_usage MB"
|
||||
}
|
||||
|
||||
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"
|
||||
}
|
||||
|
||||
wait_for_server() {
|
||||
# wait for vllm server to start
|
||||
# return 1 if vllm server crashes
|
||||
timeout 1200 bash -c '
|
||||
until curl -s localhost:8000/v1/completions > /dev/null; do
|
||||
sleep 1
|
||||
done' && return 0 || return 1
|
||||
}
|
||||
|
||||
run_serving_tests() {
|
||||
# run serving tests using `benchmark_serving.py`
|
||||
# $1: a json file specifying serving test cases
|
||||
|
||||
local serving_test_file
|
||||
serving_test_file=$1
|
||||
|
||||
# Iterate over serving tests
|
||||
jq -c '.[]' "$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_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 $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
# append vllm to the test name
|
||||
test_name=vllm_$test_name
|
||||
|
||||
|
||||
# get common parameters
|
||||
common_params=$(echo "$params" | jq -r '.common_parameters')
|
||||
model=$(echo "$common_params" | jq -r '.model')
|
||||
tp=$(echo "$common_params" | jq -r '.tp')
|
||||
dataset_name=$(echo "$common_params" | jq -r '.dataset_name')
|
||||
dataset_path=$(echo "$common_params" | jq -r '.dataset_path')
|
||||
port=$(echo "$common_params" | jq -r '.port')
|
||||
num_prompts=$(echo "$common_params" | jq -r '.num_prompts')
|
||||
|
||||
# get client and server arguments
|
||||
server_params=$(echo "$params" | jq -r '.vllm_server_parameters')
|
||||
client_params=$(echo "$params" | jq -r '.vllm_client_parameters')
|
||||
server_args=$(json2args "$server_params")
|
||||
client_args=$(json2args "$client_params")
|
||||
qps_list=$(echo "$params" | jq -r '.qps_list')
|
||||
qps_list=$(echo "$qps_list" | jq -r '.[] | @sh')
|
||||
echo "Running over qps list $qps_list"
|
||||
|
||||
# check if there is enough GPU to run the test
|
||||
if [[ $gpu_count -lt $tp ]]; then
|
||||
echo "Required tensor-parallel-size $tp but only $gpu_count GPU found. Skip testcase $test_name."
|
||||
continue
|
||||
fi
|
||||
|
||||
if echo "$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 vllm.entrypoints.openai.api_server \
|
||||
-tp $tp \
|
||||
--model $model \
|
||||
--port $port \
|
||||
$server_args"
|
||||
else
|
||||
echo "Key 'fp8' does not exist in common params."
|
||||
server_command="python3 \
|
||||
-m vllm.entrypoints.openai.api_server \
|
||||
-tp $tp \
|
||||
--model $model \
|
||||
--port $port \
|
||||
$server_args"
|
||||
fi
|
||||
|
||||
# run the server
|
||||
echo "Running test case $test_name"
|
||||
echo "Server command: $server_command"
|
||||
eval "$server_command" &
|
||||
|
||||
# wait until the server is alive
|
||||
wait_for_server
|
||||
if [ $? -eq 0 ]; then
|
||||
echo ""
|
||||
echo "vllm server is up and running."
|
||||
else
|
||||
echo ""
|
||||
echo "vllm failed to start within the timeout period."
|
||||
break
|
||||
fi
|
||||
|
||||
# iterate over different QPS
|
||||
for qps in $qps_list; do
|
||||
# remove the surrounding single quote from qps
|
||||
if [[ "$qps" == *"inf"* ]]; then
|
||||
echo "qps was $qps"
|
||||
qps="inf"
|
||||
echo "now qps is $qps"
|
||||
fi
|
||||
|
||||
new_test_name=$test_name"_qps_"$qps
|
||||
|
||||
client_command="python3 benchmark_serving.py \
|
||||
--backend vllm \
|
||||
--model $model \
|
||||
--dataset-name $dataset_name \
|
||||
--dataset-path $dataset_path \
|
||||
--num-prompts $num_prompts \
|
||||
--port $port \
|
||||
--save-result \
|
||||
--result-dir $RESULTS_FOLDER \
|
||||
--result-filename ${new_test_name}.json \
|
||||
--request-rate $qps \
|
||||
$client_args"
|
||||
|
||||
echo "Running test case $test_name with qps $qps"
|
||||
echo "Client command: $client_command"
|
||||
|
||||
eval "$client_command"
|
||||
|
||||
# record the benchmarking commands
|
||||
jq_output=$(jq -n \
|
||||
--arg server "$server_command" \
|
||||
--arg client "$client_command" \
|
||||
--arg gpu "$gpu_type" \
|
||||
--arg engine "vllm" \
|
||||
'{
|
||||
server_command: $server,
|
||||
client_command: $client,
|
||||
gpu_type: $gpu,
|
||||
engine: $engine
|
||||
}')
|
||||
echo "$jq_output" >"$RESULTS_FOLDER/${new_test_name}.commands"
|
||||
|
||||
done
|
||||
|
||||
# clean up
|
||||
kill_gpu_processes
|
||||
rm -rf /root/.cache/huggingface/*
|
||||
done
|
||||
}
|
||||
|
||||
|
||||
upload_to_buildkite() {
|
||||
# upload the benchmarking results to buildkite
|
||||
|
||||
# if the agent binary is not found, skip uploading the results, exit 0
|
||||
if [ ! -f /workspace/buildkite-agent ]; then
|
||||
echo "buildkite-agent binary not found. Skip uploading the results."
|
||||
return 0
|
||||
fi
|
||||
# /workspace/buildkite-agent annotate --style "success" --context "benchmark-results" --append < $RESULTS_FOLDER/${CURRENT_LLM_SERVING_ENGINE}_nightly_results.md
|
||||
/workspace/buildkite-agent artifact upload "$RESULTS_FOLDER/*"
|
||||
}
|
||||
|
||||
main() {
|
||||
|
||||
check_gpus
|
||||
# enter vllm directory
|
||||
cd $VLLM_SOURCE_CODE_LOC/benchmarks
|
||||
declare -g RESULTS_FOLDER=results/
|
||||
mkdir -p $RESULTS_FOLDER
|
||||
BENCHMARK_ROOT=../.buildkite/nightly-benchmarks/
|
||||
|
||||
export CURRENT_LLM_SERVING_ENGINE=vllm
|
||||
run_serving_tests $BENCHMARK_ROOT/tests/nightly-tests.json
|
||||
|
||||
python3 -m pip install tabulate pandas
|
||||
python3 $BENCHMARK_ROOT/scripts/summary-nightly-results.py
|
||||
upload_to_buildkite
|
||||
|
||||
}
|
||||
|
||||
main "$@"
|
||||
@@ -0,0 +1,76 @@
|
||||
import datetime
|
||||
import json
|
||||
import os
|
||||
from pathlib import Path
|
||||
|
||||
import pandas as pd
|
||||
from tabulate import tabulate
|
||||
|
||||
results_folder = Path("results/")
|
||||
|
||||
# serving results and the keys that will be printed into markdown
|
||||
serving_results = []
|
||||
serving_column_mapping = {
|
||||
"test_name": "Test name",
|
||||
"gpu_type": "GPU",
|
||||
"completed": "Successful req.",
|
||||
"request_throughput": "Tput (req/s)",
|
||||
"mean_ttft_ms": "Mean TTFT (ms)",
|
||||
"std_ttft_ms": "Std TTFT (ms)",
|
||||
"mean_itl_ms": "Mean ITL (ms)",
|
||||
"std_itl_ms": "Std ITL (ms)",
|
||||
"input_throughput": "Input Tput (tok/s)",
|
||||
"output_throughput": "Output Tput (tok/s)",
|
||||
"engine": "Engine",
|
||||
}
|
||||
|
||||
if __name__ == "__main__":
|
||||
|
||||
# collect results
|
||||
for test_file in results_folder.glob("*.json"):
|
||||
|
||||
with open(test_file, "r") as f:
|
||||
raw_result = json.loads(f.read())
|
||||
|
||||
# attach the benchmarking command to raw_result
|
||||
with open(test_file.with_suffix(".commands"), "r") as f:
|
||||
command = json.loads(f.read())
|
||||
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
|
||||
|
||||
serving_results = pd.DataFrame.from_dict(serving_results)
|
||||
|
||||
if not serving_results.empty:
|
||||
serving_results = serving_results[list(
|
||||
serving_column_mapping.keys())].rename(
|
||||
columns=serving_column_mapping)
|
||||
|
||||
serving_md_table_with_headers = tabulate(serving_results,
|
||||
headers='keys',
|
||||
tablefmt='pipe',
|
||||
showindex=False)
|
||||
# remove the first line of header
|
||||
serving_md_table_lines = serving_md_table_with_headers.split('\n')
|
||||
serving_md_table_without_header = '\n'.join(serving_md_table_lines[2:])
|
||||
|
||||
prefix = datetime.datetime.now().strftime("%Y-%m-%d_%H-%M-%S")
|
||||
prefix = prefix + "_" + os.environ.get("CURRENT_LLM_SERVING_ENGINE")
|
||||
|
||||
# document benchmarking results in markdown
|
||||
with open(results_folder / f"{prefix}_nightly_results.md", "w") as f:
|
||||
# document results with header.
|
||||
# for those who wants to reproduce our benchmark.
|
||||
f.write(serving_md_table_with_headers)
|
||||
f.write('\n')
|
||||
|
||||
# document benchmarking results in json
|
||||
with open(results_folder / f"{prefix}_nightly_results.json", "w") as f:
|
||||
|
||||
results = serving_results.to_dict(orient='records')
|
||||
f.write(json.dumps(results))
|
||||
@@ -0,0 +1,17 @@
|
||||
#!/bin/sh
|
||||
TOKEN=$(curl -s -L "https://public.ecr.aws/token?service=public.ecr.aws&scope=repository:q9t5s3a7/vllm-ci-test-repo:pull" | jq -r .token)
|
||||
URL="https://public.ecr.aws/v2/q9t5s3a7/vllm-ci-test-repo/manifests/$BUILDKITE_COMMIT"
|
||||
|
||||
retries=0
|
||||
while [ $retries -lt 1000 ]; do
|
||||
if [ $(curl -s -L -H "Authorization: Bearer $TOKEN" -o /dev/null -w "%{http_code}" $URL) -eq 200 ]; then
|
||||
exit 0
|
||||
fi
|
||||
|
||||
echo "Waiting for image to be available..."
|
||||
|
||||
retries=$((retries + 1))
|
||||
sleep 5
|
||||
done
|
||||
|
||||
exit 1
|
||||
@@ -0,0 +1,67 @@
|
||||
|
||||
## Latency tests
|
||||
|
||||
This test suite aims to test vllm's end-to-end latency under a controlled setup.
|
||||
|
||||
- Input length: 32 tokens.
|
||||
- Output length: 128 tokens.
|
||||
- Batch size: fixed (8).
|
||||
- Models: llama-3 8B, llama-3 70B, mixtral 8x7B.
|
||||
- Evaluation metrics: end-to-end latency (mean, median, p99).
|
||||
|
||||
### Latency benchmarking results
|
||||
|
||||
{latency_tests_markdown_table}
|
||||
|
||||
## Throughput tests
|
||||
|
||||
This test suite aims to test vllm's throughput.
|
||||
|
||||
- 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.
|
||||
- Models: llama-3 8B, llama-3 70B, mixtral 8x7B.
|
||||
- Evaluation metrics: throughput.
|
||||
|
||||
### Throughput benchmarking results
|
||||
|
||||
{throughput_tests_markdown_table}
|
||||
|
||||
## Serving tests
|
||||
|
||||
This test suite aims to test vllm's real serving metrics.
|
||||
|
||||
- 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).
|
||||
- Models: llama-3 8B, llama-3 70B, mixtral 8x7B.
|
||||
- Evaluation metrics: throughput, TTFT (time to the first token, with mean, median and p99), ITL (inter-token latency, with mean, median and p99).
|
||||
|
||||
### Serving benchmarking results
|
||||
|
||||
{serving_tests_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.
|
||||
|
||||
+3
-3
@@ -2,7 +2,7 @@
|
||||
{
|
||||
"test_name": "latency_llama8B_tp1",
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
||||
"model": "meta-llama/Meta-Llama-3-8B",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"num_iters_warmup": 5,
|
||||
@@ -12,7 +12,7 @@
|
||||
{
|
||||
"test_name": "latency_llama70B_tp4",
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
||||
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
|
||||
"tensor_parallel_size": 4,
|
||||
"load_format": "dummy",
|
||||
"num-iters-warmup": 5,
|
||||
@@ -29,4 +29,4 @@
|
||||
"num-iters": 15
|
||||
}
|
||||
}
|
||||
]
|
||||
]
|
||||
@@ -0,0 +1,116 @@
|
||||
[
|
||||
{
|
||||
"test_name": "llama8B_tp1",
|
||||
"qps_list": [4],
|
||||
"common_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-8B",
|
||||
"tp": 1,
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 500,
|
||||
"port": 8000
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "float16",
|
||||
"max_batch_size": 256,
|
||||
"max_input_len": 4096,
|
||||
"max_output_len": 4096,
|
||||
"trt_llm_version": "r24.04"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"disable_log_requests": ""
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "llama70B_tp4",
|
||||
"qps_list": [2],
|
||||
"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
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "float16",
|
||||
"max_batch_size": 256,
|
||||
"max_input_len": 4096,
|
||||
"max_output_len": 4096,
|
||||
"trt_llm_version": "r24.04"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"disable_log_requests": ""
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "mixtral8x7B_tp2",
|
||||
"qps_list": [2],
|
||||
"common_parameters": {
|
||||
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
||||
"tp": 2,
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 500,
|
||||
"port": 8000
|
||||
},
|
||||
"lmdeploy_server_parameters": {
|
||||
},
|
||||
"lmdeploy_client_parameters": {
|
||||
},
|
||||
"tgi_server_parameters": {
|
||||
},
|
||||
"tgi_client_parameters": {
|
||||
"endpoint": "/generate_stream"
|
||||
},
|
||||
"trt_server_parameters": {
|
||||
"model_type": "llama",
|
||||
"model_dtype": "float16",
|
||||
"max_batch_size": 256,
|
||||
"max_input_len": 4096,
|
||||
"max_output_len": 4096,
|
||||
"trt_llm_version": "r24.04"
|
||||
},
|
||||
"trt_client_parameters": {
|
||||
"endpoint": "/v2/models/ensemble/generate_stream"
|
||||
},
|
||||
"vllm_server_parameters": {
|
||||
"disable_log_stats": "",
|
||||
"disable_log_requests": ""
|
||||
},
|
||||
"vllm_client_parameters": {
|
||||
}
|
||||
}
|
||||
]
|
||||
@@ -0,0 +1,59 @@
|
||||
[
|
||||
{
|
||||
"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,
|
||||
"swap_space": 16,
|
||||
"disable_log_stats": "",
|
||||
"disable_log_requests": "",
|
||||
"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
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_llama70B_tp4_sharegpt",
|
||||
"qps_list": [1, 4, 16, "inf"],
|
||||
"server_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
|
||||
"tensor_parallel_size": 4,
|
||||
"swap_space": 16,
|
||||
"disable_log_stats": "",
|
||||
"disable_log_requests": "",
|
||||
"load_format": "dummy"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
|
||||
"backend": "vllm",
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 200
|
||||
}
|
||||
},
|
||||
{
|
||||
"test_name": "serving_mixtral8x7B_tp2_sharegpt",
|
||||
"qps_list": [1, 4, 16, "inf"],
|
||||
"server_parameters": {
|
||||
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
||||
"tensor_parallel_size": 2,
|
||||
"swap_space": 16,
|
||||
"disable_log_stats": "",
|
||||
"disable_log_requests": "",
|
||||
"load_format": "dummy"
|
||||
},
|
||||
"client_parameters": {
|
||||
"model": "mistralai/Mixtral-8x7B-Instruct-v0.1",
|
||||
"backend": "vllm",
|
||||
"dataset_name": "sharegpt",
|
||||
"dataset_path": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
"num_prompts": 200
|
||||
}
|
||||
}
|
||||
]
|
||||
+3
-3
@@ -2,7 +2,7 @@
|
||||
{
|
||||
"test_name": "throughput_llama8B_tp1",
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-8B-Instruct",
|
||||
"model": "meta-llama/Meta-Llama-3-8B",
|
||||
"tensor_parallel_size": 1,
|
||||
"load_format": "dummy",
|
||||
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
@@ -13,7 +13,7 @@
|
||||
{
|
||||
"test_name": "throughput_llama70B_tp4",
|
||||
"parameters": {
|
||||
"model": "meta-llama/Meta-Llama-3.1-70B-Instruct",
|
||||
"model": "meta-llama/Meta-Llama-3-70B-Instruct",
|
||||
"tensor_parallel_size": 4,
|
||||
"load_format": "dummy",
|
||||
"dataset": "./ShareGPT_V3_unfiltered_cleaned_split.json",
|
||||
@@ -32,4 +32,4 @@
|
||||
"backend": "vllm"
|
||||
}
|
||||
}
|
||||
]
|
||||
]
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user