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). @ deepseek_v3

AlpinDale a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)		пре 2 месеци
..
activation.cpp	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 6 месеци
attention.cpp	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 6 месеци
cache.cpp	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 6 месеци
cpu_types.hpp	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 6 месеци
cpu_types_vsx.hpp	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 6 месеци
cpu_types_x86.hpp	f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017)	пре 3 месеци
dnnl_helper.hpp	f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017)	пре 3 месеци
layernorm.cpp	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 6 месеци
pos_encoding.cpp	f1d0b77c92 [0.6.0] Release Candidate (#481)	пре 6 месеци
quant.cpp	f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017)	пре 3 месеци
torch_bindings.cpp	a113309876 kernel: add meta functions for ops to prevent graph breaks (#1019)	пре 2 месеци
utils.cpp	f2b6dc3872 cpu: add support for W8A8 quantization via compressed-tensor (#1017)	пре 3 месеци