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). @ dynatempagain

AlpinDale a401f8e05d feat: per-tensor token epilogue kernels (#630)		4 сар өмнө
..
all_reduce	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
attention	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
backup	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	9 сар өмнө
core	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
cpu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
hadamard	5d288aa76c feat: add fast hadamard transformation kernels (#232)	11 сар өмнө
mamba	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
moe	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
prepare_inputs	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
punica	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
quantization	a401f8e05d feat: per-tensor token epilogue kernels (#630)	4 сар өмнө
activation_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
cache.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
cache_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
cuda_compat.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
cuda_utils.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
cuda_utils_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
dispatch_utils.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
layernorm_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
ops.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
pos_encoding_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
reduction.cuh	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 сар өмнө
torch_bindings.cpp	a401f8e05d feat: per-tensor token epilogue kernels (#630)	4 сар өмнө