Matthew BonanniandWentao Ye 1a1fc3bbc0 [Attention][MLA] Make FLASHINFER_MLA the default MLA backend on Blackwell, and TRTLLM the default prefill (#32615) ...

Signed-off-by: Matthew Bonanni <mbonanni@redhat.com>
Co-authored-by: Wentao Ye <44945378+yewentao256@users.noreply.github.com>

2026-01-19 18:41:34 -05:00

..

__init__.py

[1/N][Attention] Restructure attention: move files (#31916)

2026-01-09 13:10:24 -08:00

chunked_local_attention.py

[6/N][Attention] Move utils to more appropriate locations (#32215)

2026-01-13 05:38:52 -08:00

cross_attention.py

[6/N][Attention] Move utils to more appropriate locations (#32215)

2026-01-13 05:38:52 -08:00

encoder_only_attention.py

[6/N][Attention] Move utils to more appropriate locations (#32215)

2026-01-13 05:38:52 -08:00

mla_attention.py

[Attention][MLA] Make FLASHINFER_MLA the default MLA backend on Blackwell, and TRTLLM the default prefill (#32615)

2026-01-19 18:41:34 -05:00

mm_encoder_attention.py

[Misc][LLaMa4] Compile LLaMa Vision Encoder (#30709)

2026-01-09 22:01:38 -05:00

static_sink_attention.py

[6/N][Attention] Move utils to more appropriate locations (#32215)

2026-01-13 05:38:52 -08:00