Popular repositories Loading

1. pxq_llama.cpp pxq_llama.cpp Public

   PXQ: PXA-native low-bit MoE quants (2/3/4-bit, E16-row scales) + fused CUDA kernels for Pascal/Volta — run a real 35B on a salvaged 12-16GB card. Fork of ik_llama.cpp.

   C++ 6 1

2. awesome-local-ai awesome-local-ai Public

   Forked from janhq/awesome-local-ai

   An awesome repository of local AI tools

   1 1

3. PXA_llama PXA_llama Public

   Run modern hybrid/MoE LLMs correctly and fast on cheap old Tesla P100 / GTX 1080 Ti cards. Fork of ik_llama.cpp: clean concurrent (np>1) Gated-DeltaNet hybrid decoding + Pascal sm_60 FP16 build tun…

   Shell