youkaichao 3cd9b5bb2d

[Core][Distributed] use existing torch.cuda.device (#4318) ...

[Core][Distributed] use existing torch.cuda.device context manager (#4318)

2024-04-24 09:00:20 -07:00

..

device_communicators

[Core][Distributed] use existing torch.cuda.device (#4318)

2024-04-24 09:00:20 -07:00

__init__.py

[Core][Refactor] move parallel_utils into vllm/distributed (#3950)

2024-04-10 15:33:30 -07:00

communication_op.py

[mypy] Add mypy type annotation part 1 (#4006)

2024-04-12 14:35:50 -07:00

parallel_state.py

[Core][Distributed] use cpu/gloo to initialize pynccl (#4248)

2024-04-23 18:32:19 -07:00

utils.py

[Core] avoid too many cuda context by caching p2p test (#4021)

2024-04-13 23:40:21 -07:00