david/aphrodite-engine

miroir de https://github.com/PygmalionAI/aphrodite-engine

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