vllm/parallel_utils at ee88a7e5f3acc1f81c52dfc45d2bdd542b4cd9ed - vllm - Luminance Code Repo

20231088/vllm

History

Woosuk Kwon 12659a0bd7

Add CUDA graph-based all reduce launcher (#26 )

2023-04-05 11:16:57 -07:00

..

tensor_parallel

Add CUDA graph-based all reduce launcher (#26 )

2023-04-05 11:16:57 -07:00

__init__.py

Support tensor parallel (#2 )

2023-03-21 13:45:42 -07:00

parallel_state.py

Add CUDA graph-based all reduce launcher (#26 )

2023-04-05 11:16:57 -07:00

README.md

Support tensor parallel (#2 )

2023-03-21 13:45:42 -07:00

utils.py

Support tensor parallel (#2 )

2023-03-21 13:45:42 -07:00

README.md

The files in this folder are ported from Megatron-LM. We only keep the codes that are used in inference.