NVIDIA / NVIDIA/TensorRT

Q-DQ nodes for int8 LayerNorm

Open
#4,084 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

Description

Is there any guidance for Q-DQ node placement when using LayerNorm? For example, if I have a convolution followed by a LayerNorm, would I put Q-DQ nodes before the LayerNorm? I am hoping to have the LayerNorm operate in int8 if possible.

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

No file, test, or entry point is named. Start by reviewing TensorRT's quantization guidance for Q-DQ placement and LayerNorm, using the convolution-followed-by-LayerNorm example in the issue. Done means providing clear guidance on whether LayerNorm can operate in int8 and where Q-DQ nodes belong.

Written by the indexing model from the issue text.

Assessment

Domain
machine-learning
Issue type
Documentation
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.