Woosuk Kwon 1cd885bd54 [V0 Deprecation] Remove V0 model runner base & simplify worker base (#25328) ...

Signed-off-by: Woosuk Kwon <woosuk.kwon@berkeley.edu>

2025-09-20 20:49:09 -07:00

..

backends

[V0 Deprecation] Remove V0 model runner base & simplify worker base (#25328)

2025-09-20 20:49:09 -07:00

layers

Directly get max encoder len from VLLM config in V1 (#24866)

2025-09-16 17:52:31 +00:00

ops

Optimize triton unified attention performance for sliding window attention (#24390)

2025-09-19 13:07:26 -06:00

utils

[Attention] FlashAttn MLA (#14258)

2025-09-04 02:47:59 -07:00

__init__.py

Remove duplicate entry in vllm.attention.__all__ (#23296)

2025-08-20 17:14:59 -07:00

layer.py

[BUG FIX][NON-CUDA]quick fix to avoid call cudagraph_unsafe in attention (#25298)

2025-09-20 04:41:23 +00:00

selector.py

[gpt-oss] Enable gpt-oss on ampere (#22714)

2025-08-12 03:21:44 -07:00