Jeff Tang comments

Results 55 comments of


                                            Jeff Tang

llama-cpp-python not using GPU on m1

Yes running the llama.cpp's main shows GPU Time: Looks like it's something related to llama_cpp_python - btw, the `CMAKE_ARGS="-DLLAMA_METAL=on" FORCE_CMAKE=1 pip install` command above installed the version 0.2.7 of llama-cpp-python.

Local LangGraph RAG agent with Llama 3 error

@IgorKasianenko I just tested the notebook till that cell and it works for me. Below are my steps after `git clone https://github.com/meta-llama/llama-cookbook` to my 2021 MBP with M1 Pro: ```...

Local LangGraph RAG agent with Llama 3 error

Yes I can reproduce the error. And also got an error in the previous cell, with a bit commented out debugging code: ``` for output in app.stream(inputs): print(output) # for...

Local LangGraph RAG agent with Llama 3 error

@rlancemartin can you please take a look?

Update/deprecate Llama 3 recipe

@IgorKasianenko Yes the tutorial needs to be updated for Llama 4 with fixes of broken links. I'm currently unable to locate a 8xH100 to confirm the guide [Llama 4 in...