[ROCm][CI] Split Entrypoints Integration (API Server 1) into 3 jobs (#37906)
Signed-off-by: Andreas Karatzas <akaratza@amd.com>
This commit is contained in:
@@ -1435,7 +1435,7 @@ steps:
|
|||||||
- pytest -v -s entrypoints/offline_mode
|
- pytest -v -s entrypoints/offline_mode
|
||||||
|
|
||||||
|
|
||||||
- label: Entrypoints Integration (API Server 1) # 1h 7m
|
- label: Entrypoints Integration (API Server openai - Part 1) # TBD
|
||||||
timeout_in_minutes: 180
|
timeout_in_minutes: 180
|
||||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi325]
|
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi325]
|
||||||
agent_pool: mi325_1
|
agent_pool: mi325_1
|
||||||
@@ -1448,10 +1448,43 @@ steps:
|
|||||||
- tests/entrypoints/test_chat_utils
|
- tests/entrypoints/test_chat_utils
|
||||||
commands:
|
commands:
|
||||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
- pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
|
- pytest -v -s entrypoints/openai/chat_completion --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py
|
||||||
|
|
||||||
|
|
||||||
|
- label: Entrypoints Integration (API Server openai - Part 2) # TBD
|
||||||
|
timeout_in_minutes: 180
|
||||||
|
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi325]
|
||||||
|
agent_pool: mi325_1
|
||||||
|
fast_check: true
|
||||||
|
torch_nightly: true
|
||||||
|
working_dir: "/vllm-workspace/tests"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- tests/entrypoints/openai
|
||||||
|
- tests/entrypoints/test_chat_utils
|
||||||
|
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/speech_to_text/
|
||||||
- pytest -v -s entrypoints/test_chat_utils.py
|
- pytest -v -s entrypoints/test_chat_utils.py
|
||||||
|
|
||||||
|
|
||||||
|
- label: Entrypoints Integration (API Server openai - Part 3) # TBD
|
||||||
|
timeout_in_minutes: 180
|
||||||
|
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi325]
|
||||||
|
agent_pool: mi325_1
|
||||||
|
fast_check: true
|
||||||
|
torch_nightly: true
|
||||||
|
working_dir: "/vllm-workspace/tests"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- tests/entrypoints/openai
|
||||||
|
- tests/entrypoints/test_chat_utils
|
||||||
|
commands:
|
||||||
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
|
- pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/speech_to_text/ --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
|
||||||
|
|
||||||
|
|
||||||
- label: Entrypoints Integration (API Server 2) #26.9m
|
- label: Entrypoints Integration (API Server 2) #26.9m
|
||||||
timeout_in_minutes: 45
|
timeout_in_minutes: 45
|
||||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi325]
|
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi325]
|
||||||
@@ -2941,7 +2974,7 @@ steps:
|
|||||||
# #
|
# #
|
||||||
#####################################################################################################################################
|
#####################################################################################################################################
|
||||||
|
|
||||||
- label: Entrypoints Integration (API Server 1) # TBD
|
- label: Entrypoints Integration (API Server openai - Part 1) # TBD
|
||||||
timeout_in_minutes: 180
|
timeout_in_minutes: 180
|
||||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
|
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
|
||||||
agent_pool: mi355_1
|
agent_pool: mi355_1
|
||||||
@@ -2954,10 +2987,43 @@ steps:
|
|||||||
- tests/entrypoints/test_chat_utils
|
- tests/entrypoints/test_chat_utils
|
||||||
commands:
|
commands:
|
||||||
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
- pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py --ignore=entrypoints/openai/completion/test_tensorizer_entrypoint.py --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
|
- pytest -v -s entrypoints/openai/chat_completion --ignore=entrypoints/openai/chat_completion/test_chat_with_tool_reasoning.py --ignore=entrypoints/openai/chat_completion/test_oot_registration.py
|
||||||
|
|
||||||
|
|
||||||
|
- label: Entrypoints Integration (API Server openai - Part 2) # TBD
|
||||||
|
timeout_in_minutes: 180
|
||||||
|
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
|
||||||
|
agent_pool: mi355_1
|
||||||
|
fast_check: true
|
||||||
|
torch_nightly: true
|
||||||
|
working_dir: "/vllm-workspace/tests"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- tests/entrypoints/openai
|
||||||
|
- tests/entrypoints/test_chat_utils
|
||||||
|
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/speech_to_text/
|
||||||
- pytest -v -s entrypoints/test_chat_utils.py
|
- pytest -v -s entrypoints/test_chat_utils.py
|
||||||
|
|
||||||
|
|
||||||
|
- label: Entrypoints Integration (API Server openai - Part 3) # TBD
|
||||||
|
timeout_in_minutes: 180
|
||||||
|
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
|
||||||
|
agent_pool: mi355_1
|
||||||
|
fast_check: true
|
||||||
|
torch_nightly: true
|
||||||
|
working_dir: "/vllm-workspace/tests"
|
||||||
|
source_file_dependencies:
|
||||||
|
- vllm/
|
||||||
|
- tests/entrypoints/openai
|
||||||
|
- tests/entrypoints/test_chat_utils
|
||||||
|
commands:
|
||||||
|
- export VLLM_WORKER_MULTIPROC_METHOD=spawn
|
||||||
|
- pytest -v -s entrypoints/openai --ignore=entrypoints/openai/chat_completion --ignore=entrypoints/openai/completion --ignore=entrypoints/openai/speech_to_text/ --ignore=entrypoints/openai/correctness/ --ignore=entrypoints/openai/tool_parsers/ --ignore=entrypoints/openai/responses
|
||||||
|
|
||||||
|
|
||||||
- label: Entrypoints Integration (API Server 2) # TBD
|
- label: Entrypoints Integration (API Server 2) # TBD
|
||||||
timeout_in_minutes: 180
|
timeout_in_minutes: 180
|
||||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
|
mirror_hardwares: [amdexperimental, amdproduction, amdgfx950nightly, amdmi355]
|
||||||
|
|||||||
Reference in New Issue
Block a user