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). @ cd9ed8623b5bdc0371c785cffdecad64d550526a

AlpinDale 8c32e49029 feat: add avx2 cpu support		vor 7 Monaten
..
activation.cpp	9d81716bfd [v0.5.3] Release Candidate (#388)	vor 10 Monaten
attention.cpp	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	vor 7 Monaten
cache.cpp	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	vor 7 Monaten
cpu_types.hpp	8c32e49029 feat: add avx2 cpu support	vor 7 Monaten
layernorm.cpp	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	vor 7 Monaten
pos_encoding.cpp	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	vor 7 Monaten
torch_bindings.cpp	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	vor 7 Monaten