microsoft / microsoft/onnxruntime

Is OnnxRt support sparse tensor input?

Open
#5,578 4 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

contributions welcome
Dominant language
C++
Stars
21.9k
Forks
4.2k
Avg merge
4d 11h
Merged PRs (30d)
184

Description

I'm wonder if onnxruntime support input a sparse tensor like scipy.sparse or torch.sparse.FloatTensor?

or if onnxruntime has a switch to open sparse tensor, like expand a tensor from (1,n) to (k,n), the memory doesn't expand k times.

- ONNX Runtime version (you are using): 1.4.0

support of sparse tensor in inference

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 names ONNX Runtime 1.4.0 and asks about sparse inputs from scipy.sparse or torch.sparse.FloatTensor, but it does not identify a file, entry point, or test. Start by locating ONNX Runtime's inference input and tensor representation code, then check existing sparse-tensor coverage. Done means the supported behavior and any required implementation scope are documented or tested.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Feature
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.