Taeksang Kim 6e98f6d8b6 Implement zero-copy GQA for multimodal and CPU (#33732) ...

Signed-off-by: Taeksang Kim <ts.kim@hyperaccel.ai>

2026-02-04 20:11:39 +00:00

..

__init__.py

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

2026-01-27 10:02:51 -05:00

attention.py

[Attention] Move MLA forward from backend to layer (#33284)

2026-01-30 19:30:00 -08:00

chunked_local_attention.py

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

2026-01-27 10:02:51 -05:00

cross_attention.py

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

2026-01-27 10:02:51 -05:00

encoder_only_attention.py

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

2026-01-27 10:02:51 -05:00

kv_transfer_utils.py

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

2026-01-27 10:02:51 -05:00

mla_attention.py

[Bugfix] Fix sparse MLA metadata building (#33579)

2026-02-03 15:29:48 -08:00

mm_encoder_attention.py

Implement zero-copy GQA for multimodal and CPU (#33732)

2026-02-04 20:11:39 +00:00

static_sink_attention.py

[5/N][Attention] Finish eliminating vllm/attention folder (#32064)

2026-01-27 10:02:51 -05:00