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). @ 3a0fdf7b9b85d83a6723865aaba5326620cf0f36

AlpinDale 3a0fdf7b9b chore: remove `image_input_type` from VLM config		пре 7 месеци
..
__init__.py	50b7c13db0 refactor: attention selector (#552)	пре 7 месеци
loader.py	3a0fdf7b9b chore: remove `image_input_type` from VLM config	пре 7 месеци
neuron.py	fca911ee0a vLLM Upstream Sync (#526)	пре 8 месеци
openvino.py	0886c361f4 feat: OpenVINO CPU backend (#576)	пре 7 месеци
tensorizer.py	964aa08a70 fix: serializer log	пре 7 месеци
utils.py	fca911ee0a vLLM Upstream Sync (#526)	пре 8 месеци
weight_utils.py	517676249c chore: update the compressed-tensors config	пре 7 месеци