linkedin / linkedin/Liger-Kernel

[feat] Add jamba support

Open
#63 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

  • #102 by @winglian — closed without merging
feature
Dominant language
Python
Stars
6.6k
Forks
603
Avg merge
1d 20h
Merged PRs (30d)
47

Description

### 🚀 The feature, motivation and pitch

model code here -- https://github.com/huggingface/transformers/blob/main/src/transformers/models/jamba/modeling_jamba.py

might be interesting to see how is a triton implementation of mixer forward compared to existing cuda forward too 🤔

### Alternatives

_No response_

### Additional context

_No response_

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.

Research direction

Start by reading Hugging Face Transformers' modeling_jamba.py and inspecting the closed linked pull request for prior work. Compare the existing CUDA mixer forward with the proposed Triton implementation, then confirm that Jamba support is covered by the repository's relevant tests and training path.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
ai, machine-learning, performance
Issue type
Feature
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.