-
Update README.md
-
Upload llama_cpp_python-0.3.16-cp311-cp311-win_amd64.whl
## llama_cpp_python 0.3.16 (cp311 win_amd64)
- CUDA-enabled Windows wheel for Python 3.11
- Embedded CUDA archs: sm_75, sm_86, sm_89, sm_120
- Sanity check: loads GGUF and generates text
**File**
- `llama_cpp_python-0.3.16-cp311-cp311-win_amd64.whl` -
Upload llama_cpp_python-0.3.16-cp312-cp312-win_amd64.whl
## llama_cpp_python 0.3.16 (cp312 win_amd64)
- CUDA-enabled Windows wheel for Python 3.12
- Embedded CUDA archs: sm_75, sm_86, sm_89, sm_120
- Sanity check: loads GGUF and generates text
**File**
- `llama_cpp_python-0.3.16-cp312-cp312-win_amd64.whl` -
initial commit
