[Refactor] Relocate tests from tests/v1/entrypoints/ to tests/entrypoints/ (#37500)
Signed-off-by: sfeng33 <4florafeng@gmail.com>
This commit is contained in:
@@ -483,19 +483,6 @@ steps:
|
||||
- pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "tensor_parallelism"
|
||||
|
||||
|
||||
- label: Entrypoints V1 # TBD
|
||||
timeout_in_minutes: 180
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250]
|
||||
agent_pool: mi250_1
|
||||
optional: true
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/v1
|
||||
commands:
|
||||
- pytest -v -s v1/entrypoints
|
||||
|
||||
|
||||
- label: V1 Sample + Logits # TBD
|
||||
timeout_in_minutes: 60
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx90anightly, amdmi250]
|
||||
@@ -1173,14 +1160,14 @@ steps:
|
||||
- vllm/v1/engine/
|
||||
- vllm/v1/worker/
|
||||
- tests/v1/distributed
|
||||
- tests/v1/entrypoints/openai/test_multi_api_servers.py
|
||||
- tests/entrypoints/openai/test_multi_api_servers.py
|
||||
- vllm/platforms/rocm.py
|
||||
commands:
|
||||
- export TORCH_NCCL_BLOCKING_WAIT=1
|
||||
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py
|
||||
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py
|
||||
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py
|
||||
- DP_SIZE=2 pytest -v -s v1/entrypoints/openai/test_multi_api_servers.py
|
||||
- DP_SIZE=2 pytest -v -s entrypoints/openai/test_multi_api_servers.py
|
||||
|
||||
|
||||
- label: Distributed Compile + RPC Tests (2 GPUs) # TBD
|
||||
@@ -1766,19 +1753,6 @@ steps:
|
||||
- pytest -v -s v1/e2e/spec_decode/test_spec_decode.py -k "eagle_correctness_heavy"
|
||||
|
||||
|
||||
- label: Entrypoints V1 # 25.7m
|
||||
timeout_in_minutes: 45
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi325]
|
||||
agent_pool: mi325_1
|
||||
optional: true
|
||||
working_dir: "/vllm-workspace/tests"
|
||||
source_file_dependencies:
|
||||
- vllm/
|
||||
- tests/v1
|
||||
commands:
|
||||
- pytest -v -s v1/entrypoints
|
||||
|
||||
|
||||
- label: V1 Spec Decode # TBD
|
||||
timeout_in_minutes: 40
|
||||
mirror_hardwares: [amdexperimental, amdproduction, amdgfx942nightly, amdmi325]
|
||||
@@ -2391,14 +2365,14 @@ steps:
|
||||
- vllm/v1/engine/
|
||||
- vllm/v1/worker/
|
||||
- tests/v1/distributed
|
||||
- tests/v1/entrypoints/openai/test_multi_api_servers.py
|
||||
- tests/entrypoints/openai/test_multi_api_servers.py
|
||||
- vllm/platforms/rocm.py
|
||||
commands:
|
||||
- export TORCH_NCCL_BLOCKING_WAIT=1
|
||||
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_async_llm_dp.py
|
||||
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_eagle_dp.py
|
||||
- TP_SIZE=1 DP_SIZE=2 pytest -v -s v1/distributed/test_external_lb_dp.py
|
||||
- DP_SIZE=2 pytest -v -s v1/entrypoints/openai/test_multi_api_servers.py
|
||||
- DP_SIZE=2 pytest -v -s entrypoints/openai/test_multi_api_servers.py
|
||||
|
||||
|
||||
- label: Distributed Compile + RPC Tests (2 GPUs) # 56.1m
|
||||
|
||||
Reference in New Issue
Block a user