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). @ exl2_return

AlpinDale 2b7cd1d4ec wip		il y a 3 mois
..
all_reduce	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
attention	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
backup	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	il y a 9 mois
core	9296d4b25d feat: dynamo support for ScalarType (#733)	il y a 3 mois
cpu	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
hadamard	5d288aa76c feat: add fast hadamard transformation kernels (#232)	il y a 11 mois
mamba	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
moe	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
prepare_inputs	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
punica	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
quantization	2b7cd1d4ec wip	il y a 3 mois
activation_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
cache.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
cache_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
cuda_compat.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
cuda_utils.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
cuda_utils_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
dispatch_utils.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
layernorm_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
ops.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
pos_encoding_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
reduction.cuh	f1d0b77c92 [0.6.0] Release Candidate (#481)	il y a 4 mois
torch_bindings.cpp	2b7cd1d4ec wip	il y a 3 mois