NVIDIA-NeMo / NVIDIA-NeMo/Export-Deploy
Support quantized m-bridge checkpoint for vLLM export
Open
Nobody has claimed this yet.
enhancement
- Dominant language
- Python
- Stars
- 42
- Forks
- 18
- Avg merge
- 1d 2h
- Merged PRs (30d)
- 8
Description
Is your feature request related to a problem? Please describe.
Currently vLLM export uses HF export and m-bridge doesn't have any HF export for quantized models with modelopt. This should be supported as well.
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 tracing the vLLM export path and its existing HF export handling, then compare how m-bridge represents quantized modelopt checkpoints. Done means quantized m-bridge checkpoints can be exported through vLLM, with coverage for the supported path.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 25/100