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). @ 141c602c39b617db3e38bf4226e1a71204102442

AlpinDale 690110a051 feat: bitsandbytes quantization		7 months ago
..
__init__.py	50b7c13db0 refactor: attention selector (#552)	7 months ago
loader.py	690110a051 feat: bitsandbytes quantization	7 months ago
neuron.py	fca911ee0a vLLM Upstream Sync (#526)	8 months ago
tensorizer.py	0cea453d36 automatically detect tensorized models	7 months ago
utils.py	fca911ee0a vLLM Upstream Sync (#526)	8 months ago
weight_utils.py	690110a051 feat: bitsandbytes quantization	7 months ago