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

[CI] Tune GPU resources for test (#2401)

Browse Source 
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
This commit is contained in:
TJian authored and GitHub committed 2026-04-01 19:37:34 +08:00
1 parent 6ef0e907af
commit 4e4bbc42a6
3 files changed
+5 -5
Download Patch File Download Diff File Expand all files Collapse all files

No files matched your search

.buildkite/test-merge.yml
+1 -1
View File
@@ -174,7 +174,7 @@ steps:
pytest -s -v tests/engine/test_async_omni_engine_abort.py
'
agents:
queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
queue: "gpu_1_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
plugins:
- docker#v5.2.0:
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
.buildkite/test-ready.yml
+2 -2
View File
@@ -180,7 +180,7 @@ steps:
pytest -s -v tests/engine/test_async_omni_engine_abort.py
'
agents:
queue: "gpu_4_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
queue: "gpu_1_queue" # g6.12xlarge instance on AWS, has 4 L4 GPU
plugins:
- docker#v5.2.0:
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
@@ -271,7 +271,7 @@ steps:
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
resources:
limits:
nvidia.com/gpu: 2
nvidia.com/gpu: 1
volumeMounts:
- name: devshm
mountPath: /dev/shm
tests/e2e/online_serving/test_mimo_audio.py
+2 -2
View File
@@ -95,7 +95,7 @@ def get_max_batch_size(size_type="few"):
@pytest.mark.advanced_model
@pytest.mark.core_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards=2)
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards=1)
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_audio_to_text_audio_001(omni_server, openai_client) -> None:
"""
@@ -128,7 +128,7 @@ def test_audio_to_text_audio_001(omni_server, openai_client) -> None:
@pytest.mark.advanced_model
@pytest.mark.omni
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards=2)
@hardware_test(res={"cuda": "L4", "rocm": "MI325"}, num_cards=1)
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
def test_text_to_text_001(omni_server, openai_client) -> None:
"""