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 ac79d115b3 add guards for prefix caching, fp8, chunked, etc		5 bulan lalu
..
backends	696f2cd59c add phi3_small support with blocksparse attention	5 bulan lalu
ops	696f2cd59c add phi3_small support with blocksparse attention	5 bulan lalu
__init__.py	a94de94c44 refactor: combine the prefill and decode into a single API (#553)	6 bulan lalu
layer.py	ac79d115b3 add guards for prefix caching, fp8, chunked, etc	5 bulan lalu
selector.py	696f2cd59c add phi3_small support with blocksparse attention	5 bulan lalu