Skip to content

Conversation

SamuelMarks
Copy link

@SamuelMarks SamuelMarks commented Aug 10, 2025

Following the resounding interesting shown in my initial PR, here's a follow-up PR.

I've taken care not to edit any of your codebase—except the root pyproject.toml + README.md—to increase the chance of patch acceptance.

See that README.md for usage tips, and here are some example runs:

ls

$ python3 -m jax_llm_examples.cli ls        
- deepseek_r1_jax
- gpt_oss
- kimi_k2
- llama3
- llama4
- qwen3

run

$ python3 -m jax_llm_examples.cli run -n qwen3

More love needs to be given to the search-path syntax (see my TODO) and the meta package needs to do better work in discerning each package's dependencies; but it's a start (and it works).

…are for meta package ; [README.md] Document new CLI
Copy link
Collaborator

@rdyro rdyro left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

CLI for models is a really cool idea as is your implementation, but it unfortunately falls outside the scope of this project.

The focus here is a high-performance reference implementation more than a runner.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants