• ZIAN HU's avatar
    feat: upgrade the 4-bit quantized T5 encoder (#320) · 0ade163c
    ZIAN HU authored
    
    
    * Updating quantized t5 encoder
    
    * Fix formatting based on pre-commit hook
    
    * Update test cases
    
    * Fixing linter issue
    
    * Fix linter reformatting
    
    * support fp4
    
    * style: make linter happy
    
    * update the fp4 lpips
    
    * Prevent downloading original t5 model
    
    * Make sure model in eval mode
    
    ---------
    Co-authored-by: default avatarmuyangli <lmxyy1999@foxmail.com>
    0ade163c
flux.1-schnell-qencoder.py 1.04 KB