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). @ sampling-kernels

AlpinDale 9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale		il y a 5 mois
..
activation.cpp	b3d2b639d2 feat: add `gelu_quick` CPU kernel	il y a 5 mois
attention.cpp	9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale	il y a 5 mois
cache.cpp	9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale	il y a 5 mois
cpu_types.hpp	271a680026 feat: inference support for PowerPC ISA	il y a 5 mois
cpu_types_vsx.hpp	271a680026 feat: inference support for PowerPC ISA	il y a 5 mois
cpu_types_x86.hpp	271a680026 feat: inference support for PowerPC ISA	il y a 5 mois
layernorm.cpp	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	il y a 5 mois
pos_encoding.cpp	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	il y a 5 mois
torch_bindings.cpp	9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale	il y a 5 mois