Richard Liu 2148441fd3

[TPU] Support single and multi-host TPUs on GKE (#7613)

2024-08-30 00:27:40 -07:00

..

device_communicators

[TPU] Support single and multi-host TPUs on GKE (#7613)

2024-08-30 00:27:40 -07:00

__init__.py

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

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

communication_op.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

parallel_state.py

[Bugfix] Fix weight loading for Chameleon when TP>1 (#7410)

2024-08-13 05:33:41 +00:00

utils.py

[MISC] Introduce pipeline parallelism partition strategies (#6920)

2024-07-31 12:02:17 -07:00