LI MOUandGitHub 53328d7536 [BUG] fix crash on flashinfer backend with cudagraph disabled, when attention group_size not in [1,2,4,8] (#7509)

2024-08-21 08:54:31 -07:00

..

backends

[BUG] fix crash on flashinfer backend with cudagraph disabled, when attention group_size not in [1,2,4,8] (#7509)

2024-08-21 08:54:31 -07:00

ops

[Core/Bugfix] Add FP8 K/V Scale and dtype conversion for prefix/prefill Triton Kernel (#7208)

2024-08-12 22:47:41 +00:00

__init__.py

[Core] Add AttentionState abstraction (#7663)

2024-08-20 18:50:45 +00:00

layer.py

[Core] Subclass ModelRunner to support cross-attention & encoder sequences (towards eventual encoder/decoder model support) (#4942)

2024-08-06 16:51:47 -04:00

selector.py

[hardware] unify usage of is_tpu to current_platform.is_tpu() (#7102)

2024-08-13 00:16:42 -07:00