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). @ 884470ec36c0f1822dbecbdbbe7ff9f3b392384a

AlpinDale 39beed0b87 Revert "Refactor AWQ support."		1 年間前
..
attention	45f6d9f923 initial refactor commit	1 年間前
activation.cpp	32844c1522 add GELU kernels and remove compile bloat	1 年間前
activation_kernels.cu	32844c1522 add GELU kernels and remove compile bloat	1 年間前
attention.cpp	24c78e7306 optimization: multi-query attention kernel	1 年間前
cache.cpp	081545bde6 fix: various CUDA kernel tweaks	1 年間前
cache_kernels.cu	32844c1522 add GELU kernels and remove compile bloat	1 年間前
dispatch_utils.h	32844c1522 add GELU kernels and remove compile bloat	1 年間前
layernorm.cpp	081545bde6 fix: various CUDA kernel tweaks	1 年間前
layernorm_kernels.cu	32844c1522 add GELU kernels and remove compile bloat	1 年間前
pos_encoding.cpp	45f6d9f923 initial refactor commit	1 年間前
pos_encoding_kernels.cu	45f6d9f923 initial refactor commit	1 年間前
reduction.cuh	081545bde6 fix: various CUDA kernel tweaks	1 年間前