poisonxa16/pxq_llama.cpp

The codec + kernel pack for cards with HBM2 and no DP4A: Pascal P100 and Volta V100, fully GPU-resident, 84 architectures, dense and MoE

cuda gguf inference llama-cpp moe p100 pascal quantization v100 volta

1 Open Issue Need Help Last updated: Sep 2, 2026

Open Issues Need Help

help wanted

The codec + kernel pack for cards with HBM2 and no DP4A: Pascal P100 and Volta V100, fully GPU-resident, 84 architectures, dense and MoE

C++

#cuda#gguf#inference#llama-cpp#moe#p100#pascal#quantization#v100#volta