NVIDIA-NeMo / NVIDIA-NeMo/Export-Deploy

Export and Deploy PTQed Megatron-Bridge Models

Open
#457 1 comment 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

PTQed mbridge models with Modelopt should be deployed via Ray and Triton.

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, entry points, or tests. Start by locating the export and deployment paths for PTQed Megatron-Bridge models, then trace how Modelopt, Ray, and Triton are integrated; done means these models can be deployed through the requested Ray and Triton flow.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
backend, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.