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). @ d9c1d4f6e5d8d7ebf60210e65093ebd63dee7459

AlpinDale d9c1d4f6e5 add awq support		1 vuosi sitten
..
attention	45f6d9f923 initial refactor commit	1 vuosi sitten
quantization	d9c1d4f6e5 add awq support	1 vuosi sitten
activation.cpp	32844c1522 add GELU kernels and remove compile bloat	1 vuosi sitten
activation_kernels.cu	32844c1522 add GELU kernels and remove compile bloat	1 vuosi sitten
attention.cpp	24c78e7306 optimization: multi-query attention kernel	1 vuosi sitten
cache.cpp	081545bde6 fix: various CUDA kernel tweaks	1 vuosi sitten
cache_kernels.cu	32844c1522 add GELU kernels and remove compile bloat	1 vuosi sitten
dispatch_utils.h	32844c1522 add GELU kernels and remove compile bloat	1 vuosi sitten
layernorm.cpp	081545bde6 fix: various CUDA kernel tweaks	1 vuosi sitten
layernorm_kernels.cu	32844c1522 add GELU kernels and remove compile bloat	1 vuosi sitten
pos_encoding.cpp	45f6d9f923 initial refactor commit	1 vuosi sitten
pos_encoding_kernels.cu	45f6d9f923 initial refactor commit	1 vuosi sitten
quantization.cpp	d9c1d4f6e5 add awq support	1 vuosi sitten
reduction.cuh	081545bde6 fix: various CUDA kernel tweaks	1 vuosi sitten