vllm/vllm/attention at e519ae097ac4c126d3d8b2f3bb5ee54f696cf8bc - vllm - Gitea: Git with a cup of tea

wassname/vllm

mirror of https://github.com/wassname/vllm.git synced 2026-07-27 11:29:03 +08:00

Files

T

History

Cody YuandGitHub e0c15758b8 [Core] Modulize prepare input and attention metadata builder (#6596 )

2024-07-23 00:45:24 +00:00

..

[Core] Modulize prepare input and attention metadata builder (#6596 )

2024-07-23 00:45:24 +00:00

[Kernel][Attention] Separate Attention.kv_scale into k_scale and v_scale (#6081 )

2024-07-16 15:31:32 -07:00

__init__.py

[Core] Refactor _prepare_model_input_tensors - take 2 (#6164 )

2024-07-17 09:37:16 -07:00

layer.py

[ Misc ] fbgemm checkpoints (#6559 )

2024-07-20 09:36:57 -07:00

selector.py

[Core] Refactor _prepare_model_input_tensors - take 2 (#6164 )

2024-07-17 09:37:16 -07:00