vllm/tests/encoder_decoder at d7a4f2207bd0ff31cacf311a05266557d66e474e - vllm - Gitea: Git with a cup of tea

wassname/vllm

mirror of https://github.com/wassname/vllm.git synced 2026-07-14 11:19:39 +08:00

Files

T

History

sroy745andGitHub a78dd3303e [Encoder Decoder] Add flash_attn kernel support for encoder-decoder models (#9559 )

2024-11-01 23:22:49 -07:00

..

__init__.py

[Encoder decoder] Add cuda graph support during decoding for encoder-decoder models (#7631 )

2024-09-17 07:35:01 -07:00

test_e2e_correctness.py

[Encoder Decoder] Add flash_attn kernel support for encoder-decoder models (#9559 )

2024-11-01 23:22:49 -07:00