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). @ control-vectors

AlpinDale a2d476183f fix: remove scipy and re-implement CSR matrix		há 5 meses atrás
..
__init__.py	696f2cd59c add phi3_small support with blocksparse attention	há 6 meses atrás
blocksparse_attention_kernel.py	696f2cd59c add phi3_small support with blocksparse attention	há 6 meses atrás
interface.py	cda0e93a10 abstract away the platform for device capability	há 5 meses atrás
utils.py	a2d476183f fix: remove scipy and re-implement CSR matrix	há 5 meses atrás