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). @ 39beed0b87cbbd93bad2b11b939a15941cf67f6f

AlpinDale 39beed0b87 Revert "Refactor AWQ support."		hace 1 año
..
common	39beed0b87 Revert "Refactor AWQ support."	hace 1 año
endpoints	6b9561ef07 adapt TGI incremental detokenization	hace 1 año
engine	39beed0b87 Revert "Refactor AWQ support."	hace 1 año
modeling	39beed0b87 Revert "Refactor AWQ support."	hace 1 año
processing	45f6d9f923 initial refactor commit	hace 1 año
task_handler	45f6d9f923 initial refactor commit	hace 1 año
transformers_utils	663dd09399 Revert "fix: detokenization with special tokens"	hace 1 año
__init__.py	2399cbd3e6 feat: bump up the version to 0.2.1	hace 1 año