Nicolò Lucchesi 066209a045 [Attention] Refactor FA block_size limitations to hybrid models only (#29084) ...

Signed-off-by: NickLucche <nlucches@redhat.com>

2025-11-22 06:38:44 -08:00

..

backends

[Attention] Refactor FA block_size limitations to hybrid models only (#29084)

2025-11-22 06:38:44 -08:00

layers

[Bugfix] Fix ChunkedLocalAttention CUDA Graph setting (#28739)

2025-11-14 14:14:46 -08:00

ops

[ROCm] Add AMD GPU support on Deepseek v3.2 and SparseMLA (#26670)

2025-11-20 02:54:01 -08:00

utils

[Misc] Refactor Attention kv transfer methods into decorator (#27816)

2025-11-12 16:05:44 +00:00

__init__.py

[Model][Mamba] Add selector for mamba attention backend and make it pluggable for other device (#26487)

2025-11-19 16:24:55 +00:00

layer.py

[Bugfix] Safeguard against missing backend in AttentionBackendEnum (#28846)

2025-11-18 10:53:44 +00:00

selector.py

[Model][Mamba] Add selector for mamba attention backend and make it pluggable for other device (#26487)

2025-11-19 16:24:55 +00:00