cuda13

Pre-built wheels for llama-cpp-python across platforms and CUDA versions

兼容50系显卡的SoftVC VITS Singing Voice Conversion-50Series-CUDA13-Pytorch2.10

Native sm_87 PyTorch build for Jetson Orin (JetPack 7.2 / L4T r39.2 / CUDA 13.2) - no PTX-JIT fallback tax

The framework for posting a more modern cuda image for llama.cpp with cuda13 for just newer cards with RPC support. Started as just learning how to compile llama.cpp custom.