david/aphrodite-engine: PygmalionAI's large-scale inference engine pygmalion.chat It is designed to serve as the inference endpoint for the PygmalionAI website, and to allow serving the Pygmalion models to a large number of users with blazing fast speeds (thanks to vLLM's Paged Attention). @ sampling-kernels

AlpinDale ba371fbbbd feat: AWQ marlin kernels (#603)		vor 5 Monaten
..
schemes	ba371fbbbd feat: AWQ marlin kernels (#603)	vor 5 Monaten
__init__.py	f4ea11b982 feat: initial support for activation quantization	vor 6 Monaten
compressed_tensors.py	9be43994fe feat: fbgemm quantization support (#601)	vor 5 Monaten
utils.py	00503b9fc1 feat: non-uniform quantization via `compressed-tensors` for llama	vor 5 Monaten