karylab_agents/vllm
1
0
Fork 0
forked from Karylab-cklius/vllm
Code Pull Requests 2 Actions 2 Packages Activity

[ROCm][CI] Moving MI300 tests to MI325 until cluster is stabilized (#45170)

Browse Source 
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
Andreas Karatzas
2026-06-10 20:26:17 +00:00
committed by GitHub
parent 5b6b536fdc
commit 16282a9c4e
7 changed files with 17 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/test_areas/attention.yaml
+1 -1
View File
@@ -15,7 +15,7 @@ steps:
- pytest -v -s v1/attention
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 70
depends_on:
- image-build-amd
.buildkite/test_areas/engine.yaml
+2 -2
View File
@@ -28,7 +28,7 @@ steps:
- pytest -v -s engine test_sequence.py test_config.py test_logger.py test_vllm_port.py test_jit_monitor.py
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 60
depends_on:
- image-build-amd
@@ -44,7 +44,7 @@ steps:
- pytest -v -s v1/engine --ignore v1/engine/test_preprocess_error_handling.py
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 40
depends_on:
- image-build-amd
.buildkite/test_areas/entrypoints.yaml
+5 -5
View File
@@ -46,7 +46,7 @@ steps:
- PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc
mirror:
amd:
device: mi300_1
device: mi325_1
depends_on:
- image-build-amd
@@ -63,7 +63,7 @@ steps:
- pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 80
depends_on:
- image-build-amd
@@ -82,7 +82,7 @@ steps:
- pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 80
depends_on:
- image-build-amd
@@ -104,7 +104,7 @@ steps:
- pytest -v -s entrypoints/anthropic
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 60
depends_on:
- image-build-amd
@@ -165,7 +165,7 @@ steps:
- pytest -s entrypoints/openai/correctness/
mirror:
amd:
device: mi300_1
device: mi325_1
depends_on:
- image-build-amd
source_file_dependencies:
.buildkite/test_areas/kernels.yaml
+1 -1
View File
@@ -87,7 +87,7 @@ steps:
parallelism: 2
mirror:
amd:
device: mi300_1
device: mi325_1
source_file_dependencies:
- csrc/quantization/
- vllm/model_executor/layers/quantization
.buildkite/test_areas/lm_eval.yaml
+1 -1
View File
@@ -14,7 +14,7 @@ steps:
- pytest -s -v evals/gsm8k/test_gsm8k_correctness.py --config-list-file=configs/models-small.txt
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 55
depends_on:
- image-build-amd
.buildkite/test_areas/models_multimodal.yaml
+4 -4
View File
@@ -15,7 +15,7 @@ steps:
- pytest -v -s models/multimodal/generation/test_ultravox.py -m core_model
mirror:
amd:
device: mi300_1
device: mi325_1
depends_on:
- image-build-amd
@@ -33,7 +33,7 @@ steps:
- pytest -v -s models/multimodal/generation/test_vit_cudagraph.py -m core_model
mirror:
amd:
device: mi300_1
device: mi325_1
depends_on:
- image-build-amd
@@ -50,7 +50,7 @@ steps:
- pytest -v -s models/multimodal/generation/test_qwen2_vl.py -m core_model
mirror:
amd:
device: mi300_1
device: mi325_1
depends_on:
- image-build-amd
@@ -155,7 +155,7 @@ steps:
- pytest -v -s models/multimodal/pooling -m 'not core_model'
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 60
depends_on:
- image-build-amd
.buildkite/test_areas/spec_decode.yaml
+3 -3
View File
@@ -39,7 +39,7 @@ steps:
- pytest -v -s v1/e2e/spec_decode -k "speculators or mtp_correctness"
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 65
depends_on:
- image-build-amd
@@ -78,7 +78,7 @@ steps:
- pytest -v -s v1/e2e/spec_decode -k "ngram or suffix"
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 65
depends_on:
- image-build-amd
@@ -103,7 +103,7 @@ steps:
- pytest -v -s v1/e2e/spec_decode -k "draft_model or no_sync or batch_inference"
mirror:
amd:
device: mi300_1
device: mi325_1
timeout_in_minutes: 50
depends_on:
- image-build-amd