NVIDIA-NeMo / NVIDIA-NeMo/Export-Deploy
Quantize M-Bridge and HF checkpoints during In-Framework Deployment
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.
During in-framework deployment, there is no option to quantize the checkpoint. Some users asked for this feature.
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
The issue names no files, tests, or entry points. Start by locating the in-framework deployment paths for M-Bridge and Hugging Face checkpoints, then clarify which quantization modes are required. Done should mean users can quantize both checkpoint types during in-framework deployment.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- huggingface, python
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100