emailvenky commited on
Commit
31ed992
·
1 Parent(s): 4ae4ae8

llama-cpp-python: prebuilt CPU wheel (fix build OOM)

Browse files
Files changed (1) hide show
  1. requirements.txt +2 -0
requirements.txt CHANGED
@@ -4,6 +4,8 @@ gradio>=6.0
4
  httpx>=0.27.0
5
  huggingface-hub>=0.23.0
6
  spaces
 
 
7
  llama-cpp-python
8
  transformers>=5.4.0
9
  torch==2.11.0
 
4
  httpx>=0.27.0
5
  huggingface-hub>=0.23.0
6
  spaces
7
+ # prebuilt CPU wheel for llama-cpp-python — avoids the slow from-source CMake compile on the Space:
8
+ --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cpu
9
  llama-cpp-python
10
  transformers>=5.4.0
11
  torch==2.11.0