1. 08 Sep, 2025 1 commit
    • Matthew Douglas's avatar
      4bit quantization for arbitrary `nn.Parameter` (#1720) · 27549fb0
      Matthew Douglas authored
      * Add parametrize util for targeting parameters outside of nn.Linear modules
      
      * Parametrize 4bit: replace existing prequantized weight
      
      * cleanup
      
      * Add caching for parametrization
      
      * Add tests
      
      * Fix tests
      
      * Guard for torch < 2.5
      
      * Guard for torch < 2.5
      
      * Another test gaurd for torch >= 2.5
      27549fb0