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). @ 72cd8494aadb5eb1a3064ccd3437bd8814c51d38

AlpinDale 72cd8494aa feat: mistral neuron support (#368)		11 mēneši atpakaļ
..
common	0f6d56b07f feat: model executor refactor (#367)	11 mēneši atpakaļ
endpoints	b361096463 fix: tokenizer when using ray (#366)	11 mēneši atpakaļ
engine	0f6d56b07f feat: model executor refactor (#367)	11 mēneši atpakaļ
executor	0f6d56b07f feat: model executor refactor (#367)	11 mēneši atpakaļ
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	1 gadu atpakaļ
lora	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	11 mēneši atpakaļ
modeling	72cd8494aa feat: mistral neuron support (#368)	11 mēneši atpakaļ
processing	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	11 mēneši atpakaļ
spec_decode	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	11 mēneši atpakaļ
task_handler	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	11 mēneši atpakaļ
transformers_utils	b361096463 fix: tokenizer when using ray (#366)	11 mēneši atpakaļ
__init__.py	0f6d56b07f feat: model executor refactor (#367)	11 mēneši atpakaļ
py.typed	1c988a48b2 fix logging and add py.typed	1 gadu atpakaļ