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). @ 0f6d56b07f5c00c5980d20e4d96aa4b769db8261

AlpinDale 0f6d56b07f feat: model executor refactor (#367)		пре 11 месеци
..
common	0f6d56b07f feat: model executor refactor (#367)	пре 11 месеци
endpoints	b361096463 fix: tokenizer when using ray (#366)	пре 11 месеци
engine	0f6d56b07f feat: model executor refactor (#367)	пре 11 месеци
executor	0f6d56b07f feat: model executor refactor (#367)	пре 11 месеци
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	пре 1 година
lora	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	пре 11 месеци
modeling	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	пре 11 месеци
processing	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	пре 11 месеци
spec_decode	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	пре 11 месеци
task_handler	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	пре 11 месеци
transformers_utils	b361096463 fix: tokenizer when using ray (#366)	пре 11 месеци
__init__.py	0f6d56b07f feat: model executor refactor (#367)	пре 11 месеци
py.typed	1c988a48b2 fix logging and add py.typed	пре 1 година