[CI] Tune GPU resources for test (#2401)
Signed-off-by: tjtanaa <tunjian.tan@embeddedllm.com>
This commit is contained in:
1 parent
6ef0e907af
commit
4e4bbc42a6
3 files changed
+5
-5
No files matched your search
@@ -174,7 +174,7 @@ steps:
|
|||||||
pytest -s -v tests/engine/test_async_omni_engine_abort.py
|
pytest -s -v tests/engine/test_async_omni_engine_abort.py
|
||||||
'
|
'
|
||||||
agents:
|
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:
|
plugins:
|
||||||
- docker#v5.2.0:
|
- docker#v5.2.0:
|
||||||
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
|
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
|
||||||
|
|||||||
@@ -180,7 +180,7 @@ steps:
|
|||||||
pytest -s -v tests/engine/test_async_omni_engine_abort.py
|
pytest -s -v tests/engine/test_async_omni_engine_abort.py
|
||||||
'
|
'
|
||||||
agents:
|
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:
|
plugins:
|
||||||
- docker#v5.2.0:
|
- docker#v5.2.0:
|
||||||
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
|
image: public.ecr.aws/q9t5s3a7/vllm-ci-test-repo:$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:$BUILDKITE_COMMIT
|
- image: 936637512419.dkr.ecr.us-west-2.amazonaws.com/vllm-ci-pull-through-cache/q9t5s3a7/vllm-ci-test-repo:$BUILDKITE_COMMIT
|
||||||
resources:
|
resources:
|
||||||
limits:
|
limits:
|
||||||
nvidia.com/gpu: 2
|
nvidia.com/gpu: 1
|
||||||
volumeMounts:
|
volumeMounts:
|
||||||
- name: devshm
|
- name: devshm
|
||||||
mountPath: /dev/shm
|
mountPath: /dev/shm
|
||||||
|
|||||||
@@ -95,7 +95,7 @@ def get_max_batch_size(size_type="few"):
|
|||||||
@pytest.mark.advanced_model
|
@pytest.mark.advanced_model
|
||||||
@pytest.mark.core_model
|
@pytest.mark.core_model
|
||||||
@pytest.mark.omni
|
@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)
|
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
|
||||||
def test_audio_to_text_audio_001(omni_server, openai_client) -> None:
|
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.advanced_model
|
||||||
@pytest.mark.omni
|
@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)
|
@pytest.mark.parametrize("omni_server", test_params, indirect=True)
|
||||||
def test_text_to_text_001(omni_server, openai_client) -> None:
|
def test_text_to_text_001(omni_server, openai_client) -> None:
|
||||||
"""
|
"""
|
||||||
|
|||||||
Reference in new issue
Block a user