NVIDIA / NVIDIA/TensorRT

request: Add ONNX opset 23 RMSNormalization support to TensorRT ONNX parser

Open
#4,639 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

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

Description

TensorRT fails to parse ONNX models that contain opset-23 RMSNormalization (unsupported op).

RMSNorm is used by modern Transformer variants; native support simplifies deployment and preserves performance/precision.

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 locating the TensorRT ONNX parser entry point and how it handles unsupported operators, then investigate the ONNX opset-23 RMSNormalization requirement described here. Done means ONNX models containing opset-23 RMSNormalization parse successfully while preserving the stated performance and precision goals.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
backend, machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
28/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.