Commit History

Author SHA1 Message Date
  AlpinDale 141672a0d4 kernels: disambiguate quantized types via a new ScalarType 5 months ago
  AlpinDale e3f07b22c3 feat: support for QQQ W4A8 quantization (#612) 5 months ago
  AlpinDale 598afb63dd chore: add ignored layers for fp8 quant 5 months ago
  AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603) 5 months ago
  AlpinDale 98cb1c4cd1 feat: support fp8 via `llm-compressor` 5 months ago