suwenzhuo

Why don't use gpu

1

## install pip install llama-cpp-python \ --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121 --no-cache-dir ## code from llama_cpp import Llama model_path="/root/model/Llama3.1-8B-Chinese-Chat-gguf/Llama3.1-8B-Chinese-Chat.Q3_K_M.gguf" model_kwargs = { "n_ctx":8192, # Context length to use "n_threads":4, # Number of CPU...

[Bug] Aborted (core dumped)

1

### Checklist - [x] 1. I have searched related issues but cannot get the expected help. - [ ] 2. The bug has not been fixed in the latest version....