Lucas Wilkinson afcb3f8863 [Attention] MLA move o_proj q_proj into cuda-graph region (#17484) ...

Signed-off-by: Lucas Wilkinson <lwilkinson@neuralmagic.com>

2025-05-02 03:16:26 +00:00

..

mla

[Attention] MLA move o_proj q_proj into cuda-graph region (#17484)

2025-05-02 03:16:26 +00:00

__init__.py

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

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

flash_attn.py

[V1] Remove num_input_tokens from attn_metadata (#17193)

2025-04-29 09:28:41 -07:00

flashinfer.py

[V1] Remove num_input_tokens from attn_metadata (#17193)

2025-04-29 09:28:41 -07:00

pallas.py

[TPU][V1] Implicitly adjust page size when there's SMEM OOM (#16871)

2025-04-21 15:43:13 -06:00

triton_attn.py

Upstream Llama4 Support to Main (#16113)

2025-04-07 08:06:27 -07:00