pytorch / pytorch/executorch

[ET-LLM] Clean up llama/model.py

Open
#8,574 0 comments 0 reactions 1 assignee View on GitHub

@larryliu0820 is already working on this.

Since Feb 19, 2025.

module: llm triaged
Dominant language
Python
Stars
5k
Forks
1.2k
Avg merge
2d 10h
Merged PRs (30d)
581

Description

🚀 The feature, motivation and pitch

Currently llama/model.py contains too much irrelevant logic (module swapping, adapting internal weights, precision conversion etc). This is very hard to maintain and users are having a hard time to understand it.

model.py should only do 1 thing:

Construct a llama eager definition and load weights.

We should refactor out the other logic into builder.py.

Alternatives

No response

Additional context

No response

RFC (Optional)

No response

cc @mergennachin @cccclai @helunwencser @jackzhxng

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.