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). @ 156f577f79c2751cabc9b823696ace6d029371d7

AlpinDale 156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)		há 7 meses atrás
..
__init__.py	9d81716bfd [v0.5.3] Release Candidate (#388)	há 10 meses atrás
abstract.py	696f2cd59c add phi3_small support with blocksparse attention	há 7 meses atrás
blocksparse_attn.py	696f2cd59c add phi3_small support with blocksparse attention	há 7 meses atrás
flash_attn.py	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	há 7 meses atrás
flashinfer.py	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	há 7 meses atrás
rocm_flash_attn.py	71a26f0998 chore: use pytorch sdpa backend to do naive attention for rocm	há 7 meses atrás
torch_sdpa.py	696f2cd59c add phi3_small support with blocksparse attention	há 7 meses atrás
xformers.py	696f2cd59c add phi3_small support with blocksparse attention	há 7 meses atrás