Li Wang c131e43e7d [Worker]Lazy import torch_npu (#184) ...

### What this PR does / why we need it?
To avoid unnecessary delays, we only import torch_npu when profilling is
enabled.

Signed-off-by: wangli <wangli858794774@gmail.com>

2025-02-27 16:52:11 +08:00

..

ops

[CI] upgrade to newest pta (#187)

2025-02-27 16:40:23 +08:00

quantization

[Core] Cherry pick from 0.7.1 to keep the main code newest (#127)

2025-02-21 17:07:37 +08:00

__init__.py

[Core] Init vllm-ascend (#3)

2025-02-05 10:53:12 +08:00

attention.py

[CI] upgrade to newest pta (#187)

2025-02-27 16:40:23 +08:00

communicator.py

[dist] revert communicator patch (#66)

2025-02-17 11:42:33 +08:00

model_runner.py

[ModelRunner] Fix cuda hard code in model runner (#155)

2025-02-27 14:16:46 +08:00

platform.py

Ray Worker Ops Optimization (#136)

2025-02-21 22:45:15 +08:00

utils.py

[Worker] Register mindie_turbo while initializing NPUWorker (#13)

2025-02-07 16:47:17 +08:00

worker.py

[Worker]Lazy import torch_npu (#184)

2025-02-27 16:52:11 +08:00