New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Update to more recent ggml format #4

Open

Phylliida opened this issue Jun 20, 2023 · 0 comments

Phylliida commented Jun 20, 2023 •

edited

Loading

I put your changes of llama.cpp into the most recent llama.cpp

Then I had to modify LLaMPPL/llamppl/llama_cpp.py to use the new code from llama_cpp_python, you can see the new file here

Probably the easier change on your end is to pull changes of your llama_cpp branch from main and edit llama_cpp.py, but here's these if needed

Edit: hmm I'm having this issue with my changes when I offload to gpu, hold on lemme look into it:

GGML_ASSERT: C:\...\llama-cpp-python\vendor\llama.cpp\ggml.c:15154: tensor->src0->backend == GGML_BACKEND_CPU

Edit edit: nvm those are just bc eval_multi doesn't have gpu support yet

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment