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). @ feat/gumbell-softmax-experiment

AlpinDale 53d391e1f2 merge 'dev' into 'main'		il y a 1 an
..
attention	53d391e1f2 merge 'dev' into 'main'	il y a 1 an
quantization	15a0454172 feat: FP8 KV Cache (#185)	il y a 1 an
activation_kernels.cu	b9b295d74e chore: backlogs 1 (#191)	il y a 1 an
cache.h	15a0454172 feat: FP8 KV Cache (#185)	il y a 1 an
cache_kernels.cu	15a0454172 feat: FP8 KV Cache (#185)	il y a 1 an
cuda_compat.h	2755a48d51 merge dev branch into main (#153)	il y a 1 an
cuda_utils.h	2755a48d51 merge dev branch into main (#153)	il y a 1 an
cuda_utils_kernels.cu	2755a48d51 merge dev branch into main (#153)	il y a 1 an
dispatch_utils.h	7e72ce0a73 feat: mixtral tensor parallelism (#193)	il y a 1 an
layernorm_kernels.cu	b9b295d74e chore: backlogs 1 (#191)	il y a 1 an
misc_kernels.cu	7e72ce0a73 feat: mixtral tensor parallelism (#193)	il y a 1 an
ops.h	7e72ce0a73 feat: mixtral tensor parallelism (#193)	il y a 1 an
pos_encoding_kernels.cu	b9b295d74e chore: backlogs 1 (#191)	il y a 1 an
pybind.cpp	7e72ce0a73 feat: mixtral tensor parallelism (#193)	il y a 1 an
reduction.cuh	2755a48d51 merge dev branch into main (#153)	il y a 1 an