Hugging Face's logo

Spaces:
sizzlebop
/
ZeroGPU-LLM-Inference
Running

App Files Community
Luigi commited on
Commit
e883a1b
·
1 Parent(s): b1544e2

specify to build llama cpp with openblas

Browse files
Files changed (1) hide show
  1. requirements.txt +1 -2
requirements.txt CHANGED
@@ -1,8 +1,7 @@
1
  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
- llama-cpp-python
5
- llama-cpp-agent
6
  huggingface_hub
7
  streamlit
8
  duckduckgo_search
 
1
  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
+ llama-cpp-python -C cmake.args="-DGGML_BLAS=ON;-DGGML_BLAS_VENDOR=OpenBLAS"
 
5
  huggingface_hub
6
  streamlit
7
  duckduckgo_search