-
Add llama-cpp-python 0.3.30 CPU wheel (portable, GGML_NATIVE=OFF) — adds gemma4 architecture support
-
Add comprehensive README with usage instructions
-
Add llama-cpp-python v0.3.22 wheel with LFM2 MoE support (JamePeng fork)
-
Rename llama_cpp_python-0.3.16-cuda-cp310-cp310-linux_x86_64.whl to llama_cpp_python-0.3.16-1cuda-cp310-cp310-linux_x86_64.whl
-
Upload llama_cpp_python-0.3.16-cp310-cp310-linux_x86_64.whl
-
add cuda version compatible with hf zerogpu
-
track .whls with lfs
-
initial commit