NVIDIA / NVIDIA/TensorRT

Perfomence: QAT and PTQ choose different Kernel

Open
#4,319 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Investigating Module:Quantization triaged
Dominant language
C++
Stars
13.4k
Forks
2.4k
Avg merge
5d 3h
Merged PRs (30d)
2

Description

Image
Image

How to set the code, make sure the QAT has the same Kernel like PTQ

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

Start by reviewing the two attached images and the QAT/PTQ configuration that produced them. Reproduce the reported kernel selection difference in TensorRT, then identify the relevant QAT and PTQ paths. Done means determining how to make QAT select the same kernel as PTQ and documenting or validating the resulting behavior.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning, performance
Issue type
Bug
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
20/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.