david/aphrodite-engine

Mirror von https://github.com/PygmalionAI/aphrodite-engine

Autor	SHA1 Nachricht	Datum
AlpinDale	e3f07b22c3 feat: support for QQQ W4A8 quantization (#612)	vor 5 Monaten
AlpinDale	49a2836d61 fix: divide-by-zero warnings in marlin kernels	vor 5 Monaten
AlpinDale	ba371fbbbd feat: AWQ marlin kernels (#603)	vor 5 Monaten
AlpinDale	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	vor 6 Monaten
AlpinDale	c66b1b57b1 Marlin 2:4 sparsity (#555)	vor 6 Monaten