NVIDIA-NeMo / NVIDIA-NeMo/Export-Deploy

Quantize M-Bridge and HF checkpoints during In-Framework Deployment

Open
#404 0 comments 0 reactions 0 assignees View on GitHub

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

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

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.