Hugging Face's logo

Spaces:
Luigi
/
ZeroGPU-LLM-Inference
Running on Zero

App Files Community
Luigi commited on
Commit
49a4dad
·
1 Parent(s): d6f7cc4

specify gpu build for llama cpp python

Browse files
Files changed (1) hide show
  1. requirements.txt +1 -1
requirements.txt CHANGED
@@ -2,7 +2,7 @@ wheel
2
  jieba @ https://www.piwheels.org/simple/jieba/jieba-0.42.1-py3-none-any.whl
3
  docopt @ https://github.com/GoogleCloudPlatform/gcloud-python-wheels/raw/refs/heads/master/wheelhouse/docopt-0.6.2-py2.py3-none-any.whl
4
  --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
5
- llama-cpp-python
6
  streamlit
7
  duckduckgo_search
8
  gradio
 
2
  jieba @ https://www.piwheels.org/simple/jieba/jieba-0.42.1-py3-none-any.whl
3
  docopt @ https://github.com/GoogleCloudPlatform/gcloud-python-wheels/raw/refs/heads/master/wheelhouse/docopt-0.6.2-py2.py3-none-any.whl
4
  --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
5
+ llama-cpp-python --no-binary=:all: --global-option=build_ext --global-option="-DLLAMA_USE_CUBLAS=1"
6
  streamlit
7
  duckduckgo_search
8
  gradio