linkedin / linkedin/Liger-Kernel
[feat] Add jamba support
Nobody has claimed this yet.
- #102 by @winglian — closed without merging
- 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
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- 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