• zhujian's avatar
    [PyTorch] Support FA3 for MLA and with CP (#1907) · c334fc46
    zhujian authored
    
    
    feature(FA3,MLA,CP):
    1. Update FA3 to commit-id 3ba6f82 (tag 2.8.0.post2 with compile error fixed), PR-1604 support hdimQK != hdimV backward
    2. Update get_attention_backend method because FA3 support MLA now
    3. Add CP MLA support for FA3
    4. Add unit tests for FA3 MLA CP
    5. Update attention doc
    Signed-off-by: default avatarzhujian <zhujian.whu.cs@gmail.com>
    c334fc46
attention.ipynb 38 KB