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		4 月之前
..
activation.cpp	b3d2b639d2 feat: add `gelu_quick` CPU kernel	5 月之前
attention.cpp	9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale	4 月之前
cache.cpp	9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale	4 月之前
cpu_types.hpp	271a680026 feat: inference support for PowerPC ISA	5 月之前
cpu_types_vsx.hpp	271a680026 feat: inference support for PowerPC ISA	5 月之前
cpu_types_x86.hpp	271a680026 feat: inference support for PowerPC ISA	5 月之前
layernorm.cpp	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	5 月之前
pos_encoding.cpp	156f577f79 feat: switch from `PYBIND11_MODULE` to `TORCH_LIBRARY` (#569)	5 月之前
torch_bindings.cpp	9d7beaa5b9 chore: separate kv_scale into k_scale and v_scale	4 月之前