prebuilt binary of ik_llama.cpp.
build with:
- msvc 14.50.35717
- WindowsSDK 10.0.26100.0
- nvcc 13.0.88
- ninja 1.13.2
compile on rtx40s, compatible with sm_89 and above. if there is problem on rtx30s, please report it.
Inference Providers
NEW
This model isn't deployed by any Inference Provider.
🙋
Ask for provider support