lukec 57eec0bfbc fix FlashMLA cudagraph config (#4691) ...

Co-authored-by: yinfan98 <1106310035@qq.com>

2025-03-24 21:06:58 -07:00

..

triton_ops

[fix] fix illegal mem access and clean up triton attention backend (#4571)

2025-03-20 02:01:52 -07:00

base_attn_backend.py

[fix] fix illegal mem access and clean up triton attention backend (#4571)

2025-03-20 02:01:52 -07:00

double_sparsity_backend.py

Misc clean up; Remove the support of jump forward (#4032)

2025-03-03 07:02:14 -08:00

flashattention_backend.py

Support FA3 as Attention backend by using --attention-backend fa3 (#4680)

2025-03-23 23:28:11 -07:00

flashinfer_backend.py

[fix] fix illegal mem access and clean up triton attention backend (#4571)

2025-03-20 02:01:52 -07:00

flashinfer_mla_backend.py

[fix] fix illegal mem access and clean up triton attention backend (#4571)

2025-03-20 02:01:52 -07:00

flashmla_backend.py

fix FlashMLA cudagraph config (#4691)

2025-03-24 21:06:58 -07:00

torch_native_backend.py

Misc clean up; Remove the support of jump forward (#4032)

2025-03-03 07:02:14 -08:00

triton_backend.py

[fix] fix illegal mem access and clean up triton attention backend (#4571)

2025-03-20 02:01:52 -07:00

utils.py

Support FlashMLA backend cuda graph (#4514)

2025-03-19 08:25:34 -07:00

vision.py

refactor: bug fixes and refactor for vlm (#4661)

2025-03-22 22:48:49 -07:00