[CI] Update entrypoints CI (#56763)
Signed-off-by: wang.yuqi <yuqi.wang@daocloud.io>
This commit is contained in:
@@ -1067,7 +1067,7 @@ steps:
|
||||
- PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc
|
||||
- pytest -v -s entrypoints/scale_out
|
||||
|
||||
- label: ":amd: (MI300) Entrypoints Integration (API Server OpenAI - Part 1)" # TBD
|
||||
- label: ":amd: (MI300) Entrypoints Integration (OpenAI API completion)" # TBD
|
||||
timeout_in_minutes: 40
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
|
||||
dind: false
|
||||
@@ -1080,9 +1080,10 @@ steps:
|
||||
- tests/entrypoints/openai
|
||||
commands:
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
|
||||
- pytest -v -s entrypoints/openai/ --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness
|
||||
|
||||
- label: ":amd: (MI300) Entrypoints Integration (API Server OpenAI - Part 2)" # TBD
|
||||
- label: ":amd: (MI300) Entrypoints Integration (OpenAI API chat_completion)" # TBD
|
||||
timeout_in_minutes: 55
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi300]
|
||||
dind: false
|
||||
@@ -1096,7 +1097,6 @@ steps:
|
||||
commands:
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- pytest -v -s entrypoints/openai/chat_completion
|
||||
- pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
|
||||
|
||||
- label: ":amd: (MI300) Entrypoints Integration (API Server Generate)" # TBD
|
||||
timeout_in_minutes: 65
|
||||
@@ -3217,7 +3217,7 @@ steps:
|
||||
- PYTHONPATH=/vllm-workspace pytest -v -s entrypoints/serve/dev/rpc
|
||||
- pytest -v -s entrypoints/scale_out
|
||||
|
||||
- label: ":amd: (MI355) Entrypoints Integration (API Server OpenAI - Part 1)" # TBD
|
||||
- label: ":amd: (MI355) Entrypoints Integration (OpenAI API completion)" # TBD
|
||||
timeout_in_minutes: 35
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
|
||||
dind: false
|
||||
@@ -3230,9 +3230,10 @@ steps:
|
||||
- tests/entrypoints/openai
|
||||
commands:
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
|
||||
- pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness
|
||||
|
||||
- label: ":amd: (MI355) Entrypoints Integration (API Server OpenAI - Part 2)" # TBD
|
||||
- label: ":amd: (MI355) Entrypoints Integration (OpenAI API chat_completion)" # TBD
|
||||
timeout_in_minutes: 50
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
|
||||
dind: false
|
||||
@@ -3246,7 +3247,6 @@ steps:
|
||||
commands:
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- pytest -v -s entrypoints/openai/chat_completion
|
||||
- pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
|
||||
|
||||
- label: ":amd: (MI355) Entrypoints Integration (API Server Generate)" # TBD
|
||||
timeout_in_minutes: 40
|
||||
|
||||
@@ -73,9 +73,9 @@ steps:
|
||||
depends_on:
|
||||
- image-build-amd
|
||||
|
||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (API Server OpenAI - Part 1)"
|
||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (OpenAI API completion)"
|
||||
device: h200_35gb
|
||||
key: entrypoints-integration-api-server-openai-part-1
|
||||
key: entrypoints-integration-api-server-openai-completion
|
||||
timeout_in_minutes: 68
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
source_file_dependencies:
|
||||
@@ -84,19 +84,20 @@ steps:
|
||||
- tests/entrypoints/openai
|
||||
commands:
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
|
||||
- pytest -v -s entrypoints/openai --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/responses --ignore=entrypoints/openai/correctness
|
||||
mirror:
|
||||
amd:
|
||||
label: ":amd: (MI300) Entrypoints Integration (API Server OpenAI - Part 1)"
|
||||
label: ":amd: (MI300) Entrypoints Integration (OpenAI API completion)"
|
||||
dind: false
|
||||
device: mi300_1
|
||||
timeout_in_minutes: 65
|
||||
depends_on:
|
||||
- image-build-amd
|
||||
|
||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (API Server OpenAI - Part 2)"
|
||||
- label: ":nvidia: (H200 MIG 35GB) Entrypoints Integration (OpenAI API chat_completion)"
|
||||
device: h200_35gb
|
||||
key: entrypoints-integration-api-server-openai-part-2
|
||||
key: entrypoints-integration-api-server-openai-chat_completion
|
||||
timeout_in_minutes: 83
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
source_file_dependencies:
|
||||
@@ -106,10 +107,9 @@ steps:
|
||||
commands:
|
||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||
- pytest -v -s entrypoints/openai/chat_completion
|
||||
- pytest -v -s entrypoints/openai/completion --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py
|
||||
mirror:
|
||||
amd:
|
||||
label: ":amd: (MI300) Entrypoints Integration (API Server OpenAI - Part 2)"
|
||||
label: ":amd: (MI300) Entrypoints Integration (OpenAI API chat_completion)"
|
||||
dind: false
|
||||
device: mi300_1
|
||||
timeout_in_minutes: 70
|
||||
|
||||
Reference in New Issue
Block a user