Skip to content

llama inference with tensor parallelism #1403

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
stefpi wants to merge 6 commits into
base: main
Choose a base branch
from
Open

llama inference with tensor parallelism #1403

stefpi wants to merge 6 commits into from

Conversation

@stefpi
Copy link

@stefpi stefpi commented Jan 10, 2026 •
edited
Loading

related to #2973 on mlx repo.

  • made llama.py use tensor parallelism if run with mlx.launch on 2 or more devices
  • also added class_predicate to quantize because it wasn’t working properly with quantized mlx models from HF

@stefpi stefpi mentioned this pull request Jan 10, 2026
Open
6 tasks
@stefpi stefpi marked this pull request as ready for review January 15, 2026 18:09
@stefpi stefpi changed the title [WIP] llama inference with tensor parallelism llama inference with tensor parallelism Jan 15, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@stefpi