William Lin ba75ad82db [refactor]: shared attention infra additions for QAT-compat (Attn-QAT 5/12) (#1383)

2026-05-23 16:19:24 -07:00

..

flash_attn_cute.py

feat: FP4 Flash Attention 4 for Blackwell GPUs (#1221)

2026-05-12 17:04:39 -07:00

flash_attn_no_pad.py

[refactor]: shared attention infra additions for QAT-compat (Attn-QAT 5/12) (#1383)

2026-05-23 16:19:24 -07:00