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). @ control-vectors

AlpinDale fa15bad2ea chore: minor AMD fixes		hace 5 meses
..
backends	fa15bad2ea chore: minor AMD fixes	hace 5 meses
ops	9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale	hace 5 meses
__init__.py	22305c91e9 refactor _prepare_model_input_tensor and attn metadata builder for most backends	hace 5 meses
layer.py	9be43994fe feat: fbgemm quantization support (#601)	hace 5 meses
selector.py	22305c91e9 refactor _prepare_model_input_tensor and attn metadata builder for most backends	hace 5 meses