anodyine/vllm-omni
1
0 Fork 0
Code Issues 4 Pull Requests 2 Actions Packages Projects Releases Wiki Activity

[ROCm] [CI] Fix AMD CI after v0.24.0 rebase (#4821)

Browse Source 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
This commit is contained in:
TJian authored and GitHub committed 2026-07-01 15:18:24 +02:00
1 parent e7b281799e
commit efc6b391e4
1 file changed
+19 -6
Download Patch File Download Diff File Expand all files Collapse all files
.buildkite/test-amd-merge.yml
+19 -6
View File
@@ -7,17 +7,29 @@ steps:
- group: ":card_index_dividers: Simple Test"
steps:
- label: "Simple · Diffusion & Model Executor Test"
- label: "Simple · Diffusion & Model Executor Test (1/2)"
agent_pool: mi325_1
depends_on: amd-build
timeout_in_minutes: 50
timeout_in_minutes: 70
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- export VLLM_ROCM_USE_AITER=0
# ignore test_teacache_extractors.py because it use rocm gemm kernel from vLLM
# that is not supported on CPU
- "timeout 40m pytest -sv tests/diffusion tests/model_executor -m 'core_model and cpu' --ignore=tests/diffusion/cache/test_teacache_extractors.py --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
# CPU tests on ROCm gpu machines are very slow, so we give them more time.
- "timeout 60m pytest -sv tests/diffusion -m 'core_model and cpu' --ignore=tests/diffusion/cache/test_teacache_extractors.py --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
- label: "Simple · Diffusion & Model Executor Test (2/2)"
agent_pool: mi325_1
depends_on: amd-build
timeout_in_minutes: 70
mirror_hardwares: [amdproduction]
grade: Blocking
commands:
- export VLLM_ROCM_USE_AITER=0
# CPU tests on ROCm gpu machines are very slow, so we give them more time.
- "timeout 60m pytest -sv tests/model_executor -m 'core_model and cpu' --cov=vllm_omni --cov-report=term-missing:skip-covered --cov-report=xml"
- label: "Simple · Other Test"
agent_pool: mi325_1
@@ -158,7 +170,7 @@ steps:
grade: Blocking
commands:
- |
timeout 20m bash -c '
timeout 50m bash -c '
export VLLM_LOGGING_LEVEL=DEBUG
export VLLM_WORKER_MULTIPROC_METHOD=spawn
export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
@@ -170,13 +182,14 @@ steps:
depends_on: amd-build
mirror_hardwares: [amdproduction]
grade: Blocking
timeout_in_minutes: 50
commands:
- |
timeout 30m bash -c '
timeout 40m bash -c '
export VLLM_LOGGING_LEVEL=DEBUG
export VLLM_WORKER_MULTIPROC_METHOD=spawn
export VLLM_ALLOW_LONG_MAX_MODEL_LEN="1"
pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py tests/e2e/offline_inference/test_qwen3_tts_base.py -m "advanced_model" --run-level "advanced_model"
pytest -s -v tests/e2e/online_serving/test_qwen3_tts_base.py tests/e2e/offline_inference/test_qwen3_tts_base.py -m 'advanced_model and cuda' --run-level 'advanced_model'
'
# TODO: Bagel test on ROCm is very unstable. @tjtanaa