Commit History

Autor SHA1 Mensaxe Data
  AlpinDale 141672a0d4 kernels: disambiguate quantized types via a new ScalarType hai 5 meses
  AlpinDale 6979ff658e chore: perform allreduce in fp32 for marlin, better logging hai 5 meses
  AlpinDale 84a9cd25c9 fix: some naming issues hai 5 meses
  AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603) hai 5 meses
  AlpinDale 7e9d4f3c71 chore: some more marlin cleanups hai 5 meses
  AlpinDale 058e629f8e chore: refactor marlin python utils hai 5 meses
  AlpinDale 88a638d793 chore: debug logs for all available endpoints hai 5 meses
  AlpinDale 98cb1c4cd1 feat: support fp8 via `llm-compressor` hai 5 meses