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). @ cfg_take3

AlpinDale bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)		преди 1 месец
..
all_reduce	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
attention	0256ed236b feat: windows support (#790)	преди 2 месеца
backup	f8dfac6372 chore: attention refactor and upstream sync apr01 (#365)	преди 9 месеца
core	0256ed236b feat: windows support (#790)	преди 2 месеца
cpu	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
hadamard	5d288aa76c feat: add fast hadamard transformation kernels (#232)	преди 11 месеца
mamba	0256ed236b feat: windows support (#790)	преди 2 месеца
moe	0256ed236b feat: windows support (#790)	преди 2 месеца
prepare_inputs	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
punica	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
quantization	f98e7b2f8c feat: add HQQ quantization support (#795)	преди 2 месеца
sampling	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	преди 1 месец
activation_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
cache.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
cache_kernels.cu	0256ed236b feat: windows support (#790)	преди 2 месеца
cuda_compat.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
cuda_utils.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
cuda_utils_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
dispatch_utils.h	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
layernorm_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
ops.h	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	преди 1 месец
pos_encoding_kernels.cu	f1d0b77c92 [0.6.0] Release Candidate (#481)	преди 4 месеца
reduction.cuh	0256ed236b feat: windows support (#790)	преди 2 месеца
torch_bindings.cpp	bfc8988116 feat: add cuda sampling kernels for top_k and top_p (#828)	преди 1 месец