Commit History

Author SHA1 Message Date
  AlpinDale 00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama 5 months ago
  AlpinDale 19340b672e chore: improve min_capability checking for `compressed-tensors` 5 months ago
  AlpinDale 500f3b654f fix: support bias term in compressed-tensors quant 5 months ago
  AlpinDale ddb3323f94 refactor: have w8a8 compressed tensors use `process_weights_after_load` for fp8 6 months ago
  AlpinDale f4ea11b982 feat: initial support for activation quantization 6 months ago