vllm/csrc/libtorch_stable/attention at main - vllm

obscura/vllm

Fork 0

mirror of https://github.com/vllm-project/vllm.git synced 2026-08-19 04:00:20 +00:00

Files

T

History

63ac04a61e [Kimi-K3] DCP support (#50484 )

Signed-off-by: girasoley <[email protected]>
Signed-off-by: Summer Yang <[email protected]>
Signed-off-by: 云挚 <[email protected]>
Co-authored-by: Claude Fable 5 <[email protected]>
Co-authored-by: 云挚 <[email protected]>
Co-authored-by: foraxe <[email protected]>
Co-authored-by: Woosuk Kwon <[email protected]>

2026-08-10 12:54:26 -07:00

dcp_utils

[Kimi-K3] DCP support (#50484 )

2026-08-10 12:54:26 -07:00

mla

[Attention] Re-enable cross-layer KV cache layout for MLA via stride-aware kernels (#45111 )

2026-06-22 06:57:02 -07:00

attention_utils.cuh

[9/n] Migrate attention and cache kernels to torch stable ABI (continued) (#43717 )

2026-05-29 04:44:45 +00:00

merge_attn_states.cu

[Model] Add Kimi K3 support: model files and kernels [1/N] (#50089 )

2026-07-29 14:10:58 +08:00