作者 | SHA1 備註 | 提交日期 |
---|---|---|
AlpinDale | 141672a0d4 kernels: disambiguate quantized types via a new ScalarType | 5 月之前 |
AlpinDale | e3f07b22c3 feat: support for QQQ W4A8 quantization (#612) | 5 月之前 |
AlpinDale | 598afb63dd chore: add ignored layers for fp8 quant | 5 月之前 |
AlpinDale | ba371fbbbd feat: AWQ marlin kernels (#603) | 5 月之前 |
AlpinDale | 98cb1c4cd1 feat: support fp8 via `llm-compressor` | 5 月之前 |