Aryan KumarandAryan Kumar d954fad9ec [perf] MiniMax H3: faster FP4 attention padding, uint8 VAE pixel path and cuDNN FP4 GEMMs (#2046) ...

Co-authored-by: Aryan Kumar <aryan5v@users.noreply.github.com>

2026-11-01 22:23:10 -08:00

..

cudnn_sdpa.py

[perf] MiniMax H3: faster FP4 attention padding, uint8 VAE pixel path and cuDNN FP4 GEMMs (#2046)

2026-11-01 22:23:10 -08:00

fa4_env_cache.py

[bugfix] FA4 JIT cache vs tuning env, MXFP8 import and scale dtype, H3 VSA gate double quantization (#2049)

2026-11-01 19:11:25 -08:00

flash_attn_cute.py

[bugfix] FA4 JIT cache vs tuning env, MXFP8 import and scale dtype, H3 VSA gate double quantization (#2049)

2026-11-01 19:11:25 -08:00

flash_attn_default.py

[feat] Add a typed environment-variable registry, policy doc, and contract test (#1896)

2026-09-29 12:50:45 -07:00

flash_attn_no_pad.py

[feat] Add a typed environment-variable registry, policy doc, and contract test (#1896)

2026-09-29 12:50:45 -07:00