NVIDIA / NVIDIA/TensorRT

i have built an app to quantize and distill models

Open
#4,700 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Feature Request
Dominant language
C++
Stars
13.4k
Forks
2.4k
Avg merge
5d 3h
Merged PRs (30d)
2

Description

I’d appreciate any help in improving my application, which I’ve been building on my own to make it easy for people to quantize and distill models with just one click. I’ve added multiple strategies and done extensive research, even though before starting this project I had never actually done any quantizing or distilling myself. My background is in building and deploying AI applications, so I decided to give this a try. I’ve reached out to plenty of developers for help but have mostly been ignored, which has been really frustrating. My main goal is to help people run heavier AI workflows on less powerful NVIDIA GPUs. this is my repository https://github.com/manat0912/QTinker.git

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 does not name a TensorRT file, test, or concrete change; it links to the external QTinker repository instead. Review that repository first and identify whether there is a specific TensorRT integration request, with an agreed scope and completion criteria, before starting work.

Written by the indexing model from the issue text.

Assessment

Tech stack
machine-learning
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
15/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.