Lucas Wilkinson 0ee3b7fc3d [Bugfix][MLA] Add logits size budget to sparse indexer prefill chunking (#36178) ...

Signed-off-by: Lucas Wilkinson <lwilkins@redhat.com>
(cherry picked from commit eb47454987)

2026-04-01 01:02:58 -07:00

..

backends

[Bugfix][MLA] Add logits size budget to sparse indexer prefill chunking (#36178)

2026-04-01 01:02:58 -07:00

ops

[Bugfix][ROCm] Fix lru_cache on paged_mqa_logits_module (#37547)

2026-03-26 19:01:05 +00:00

__init__.py

[V1] Implement vLLM V1 [1/N] (#9289)

2024-10-22 01:24:07 -07:00

backend.py

[Attention] Support distinguishing between short extends and decodes (#37303)

2026-03-20 10:49:36 -07:00

selector.py

[Bugfix][Minor] Fix potential NameError in mamba backend selector and misc typos (#35886)

2026-03-26 11:59:24 -04:00