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). @ bitnet

AlpinDale 9bbc75d2e3 wip		il y a 5 mois
..
attention	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	il y a 5 mois
common	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	il y a 5 mois
distributed	5b0c11d190 support pipeline parallel pynccl groups	il y a 5 mois
endpoints	696f2cd59c add phi3_small support with blocksparse attention	il y a 5 mois
engine	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	il y a 5 mois
executor	5b0c11d190 support pipeline parallel pynccl groups	il y a 5 mois
kv_quant	e42a78381a feat: switch from pylint to ruff (#322)	il y a 10 mois
lora	5b0c11d190 support pipeline parallel pynccl groups	il y a 5 mois
modeling	9bbc75d2e3 wip	il y a 5 mois
processing	0d15aa3ab3 fix prefix caching for block manager v2	il y a 5 mois
quantization	5884e0b904 add bitnetforcausallm support	il y a 5 mois
spec_decode	344ddaac5a properly disable speculative decoding	il y a 5 mois
task_handler	5b0c11d190 support pipeline parallel pynccl groups	il y a 5 mois
transformers_utils	5884e0b904 add bitnetforcausallm support	il y a 5 mois
__init__.py	be8154a8a0 feat: proper embeddings API with e5-mistral-7b support	il y a 5 mois
py.typed	1c988a48b2 fix logging and add py.typed	il y a 1 an