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). @ tools-api

AlpinDale 6144150398 chore: use scalar type to dispatch to different `gptq_marlin` kernels (#689)		4 mesiacov pred
..
all_reduce	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
attention	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
backup	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	9 mesiacov pred
core	6144150398 chore: use scalar type to dispatch to different `gptq_marlin` kernels (#689)	4 mesiacov pred
cpu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
hadamard	5d288aa76c feat: add fast hadamard transformation kernels (#232)	11 mesiacov pred
mamba	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
moe	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
prepare_inputs	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
punica	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
quantization	6144150398 chore: use scalar type to dispatch to different `gptq_marlin` kernels (#689)	4 mesiacov pred
activation_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
cache.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
cache_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
cuda_compat.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
cuda_utils.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
cuda_utils_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
dispatch_utils.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
layernorm_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
ops.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
pos_encoding_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
reduction.cuh	f1d0b77c92 [0.6.0] Release Candidate (#481)	4 mesiacov pred
torch_bindings.cpp	a401f8e05d feat: per-tensor token epilogue kernels (#630)	4 mesiacov pred