mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-01-13 22:18:36 +08:00
parent
14af1593a3
commit
cc71b4a6f0
@ -299,7 +299,7 @@ l0_dgx_h100:
|
||||
backend: pytorch
|
||||
orchestrator: ray
|
||||
tests:
|
||||
- unittest/_torch/ray_orchestrator/multi_gpu -m "gpu4" TIMEOUT (3)
|
||||
- unittest/_torch/ray_orchestrator/multi_gpu -m "gpu4"
|
||||
- unittest/llmapi/test_async_llm.py -m "gpu4"
|
||||
- ray_orchestrator/RL/test_rl_perf_reproduce.py::test_rl_perf_reproduce[tp2_2instances]
|
||||
- ray_orchestrator/RL/test_rl_perf_reproduce.py::test_rl_perf_reproduce[tp1_4instances]
|
||||
|
||||
Loading…
Reference in New Issue
Block a user