llama-cpp-python
cuda
nvidia
blackwell
windows
prebuilt-wheels
python
machine-learning
large-language-models
gpu-acceleration
Instructions to use marcorez8/llama-cpp-python-windows-blackwell-cuda with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- llama-cpp-python
How to use marcorez8/llama-cpp-python-windows-blackwell-cuda with llama-cpp-python:
# !pip install llama-cpp-python from llama_cpp import Llama llm = Llama.from_pretrained( repo_id="marcorez8/llama-cpp-python-windows-blackwell-cuda", filename="{{GGUF_FILE}}", )output = llm( "Once upon a time,", max_tokens=512, echo=True ) print(output)
- Notebooks
- Google Colab
- Kaggle
- Xet hash:
- 7a7c11516d398bed6b8320129a9dd75fdbd6619c3888223987ed0b77cb489cd1
- Size of remote file:
- 65.9 MB
- SHA256:
- d5f6f9a7adfbf1d2e26b56648123c5195daea6c887f9e5ed2fe1228d4a51a753
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.