Yongye ZhuandRoger Wang 0d2732dd91 [MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 prefill + decode on Blackwell (#41778) ...

Signed-off-by: Yongye Zhu <zyy1102000@gmail.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Roger Wang <hey@rogerw.io>

2026-05-13 23:48:02 -07:00

..

mla_decode.yaml

[MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 prefill + decode on Blackwell (#41778)

2026-05-13 23:48:02 -07:00

mla_mixed_batch.yaml

[Benchmark] Improvements to attention benchmark script (#37115)

2026-03-16 22:22:40 +00:00

mla_prefill.yaml

[MLA Attention Backend] Add TOKENSPEED_MLA backend for DSR1/Kimi K25 prefill + decode on Blackwell (#41778)

2026-05-13 23:48:02 -07:00

mla_sparse_decode.yaml

[Benchmark] Improvements to attention benchmark script (#37115)

2026-03-16 22:22:40 +00:00

mla_sparse_prefill.yaml

[Attention] Use FA4 for MLA prefill (#34732)

2026-03-12 12:10:17 -04:00

reorder_threshold.yaml

[Attention] Add FlashInfer Sparse MLA backend (#33451)

2026-02-12 17:21:54 +00:00

speculative_decode.yaml

[Attention] Add FlashInfer Sparse MLA backend (#33451)

2026-02-12 17:21:54 +00:00

standard_attention.yaml

[Attention] Add FlashInfer Sparse MLA backend (#33451)

2026-02-12 17:21:54 +00:00