NVIDIA / NVIDIA/Deep-Learning-Accelerator-SW

Clarification on ONNX operator support (Ceil operator on DriveOS Orin)

Open
#32 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
236
Forks
24
PR merge metrics
No merged PRs in 30d

Description

In the following file:

operators/README.md

DLA operator functionality is exposed through the TensorRT builder, which internally links to DLA SW libraries (see DLA Workflow). While some ONNX operators or functions may already be available in DLA SW, TensorRT may not expose them yet. See below for the support matrix of ONNX operators & functions on Orin DLA. If you are interested in a specific DLA operator that is not supported through TensorRT yet, feel free to raise a GitHub Issue and/or inform your NVIDIA representative (in particular for NVIDIA DRIVE customers).

I am looking at a model with the Ceil operator on DriveOS 6.0.9.0, I can raise a TensorRT issue if this operator is really a blocking issue for building the model on DLA. But I wanted some clarification on what the above passage really means. So for the example of the Ceil operator, referencing the table, this means that the DLA SW library supports it but that there is no way TensorRT supports building a model with Ceil on DLA until TRT support is added? Even with the following versions:
DRIVE Orin (Automotive) DRIVE OS 6.0.9.0 DLA 3.14.2 TensorRT 8.6.12

Thanks.

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 with operators/README.md and review the Orin DLA ONNX operator support matrix alongside the cited DRIVE OS, DLA, and TensorRT versions. The issue seeks clarification of whether Ceil is supported by DLA SW but unavailable through TensorRT; done would be a clear, version-specific explanation or documentation correction.

Written by the indexing model from the issue text.

Assessment

Domain
documentation, machine-learning
Issue type
Documentation
Difficulty
2/5
Estimated time
1-3 hours
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.