rongfu.leng 5afd3276df [Feature] Add process_weights_after_loading to AttentionImpl (#26870) ...

Signed-off-by: rongfu.leng <rongfu.leng@daocloud.io>

2025-10-16 08:02:30 -07:00

..

backends

[Feature] Add process_weights_after_loading to AttentionImpl (#26870)

2025-10-16 08:02:30 -07:00

layers

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

ops

[DCP] Support Decode Context Parallel (DCP) for GQA with FlashAttention (#24864)

2025-10-14 13:07:50 +00:00

utils

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00

__init__.py

Convert formatting to use ruff instead of yapf + isort (#26247)

2025-10-05 07:06:22 -07:00

layer.py

[Feature] Add process_weights_after_loading to AttentionImpl (#26870)

2025-10-16 08:02:30 -07:00

selector.py

Update Optional[x] -> x | None and Union[x, y] to x | y (#26633)

2025-10-12 09:51:31 -07:00