Export llm #12

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

Open

awni wants to merge 2 commits into main from export_llm

Member

awni commented Mar 14, 2025

Comments:

So far only tested and working with model_type="llama"
C++ does tokenization and streaming detokenization but no chat templates
C++ is same speed as Python.
Compilation helps both C++ and Python. On M1 Max it's about 0.7 toks/sec for 4-bit LLama 3 8B. Toks/sec goes from 61.5 to 62.2.

awni added 2 commits

January 8, 2025 17:07


          export and run llama in C++

49f19af


          some cleanup

4f4d5c8

awni mentioned this pull request

Export and run LLMs in C++ ml-explore/mlx-examples#1197

Closed

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

Labels

None yet