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). @ 8fa608aeb734964752332d3ed06b9425b6c5a7a4

AlpinDale 8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)		1 vuosi sitten
..
attention	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
quantization	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
activation_kernels.cu	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
cache.h	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
cache_kernels.cu	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
cuda_compat.h	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
cuda_utils.h	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
cuda_utils_kernels.cu	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
dispatch_utils.h	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
layernorm_kernels.cu	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
ops.h	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
pos_encoding_kernels.cu	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
pybind.cpp	8fa608aeb7 feat: replace Ray with NCCL for control plane comms (#221)	1 vuosi sitten
reduction.cuh	2755a48d51 merge dev branch into main (#153)	1 vuosi sitten