openvinotoolkit/openvino

[Good First Issue]: support aten::tensordot

Open

#29,651 opened on Mar 24, 2025

View on GitHub
 (6 comments) (0 reactions) (1 assignee)C++ (3,229 forks)auto 404
category: PyTorch FEgood first issueno_stale

Repository metrics

Stars
 (10,286 stars)
PR merge metrics
 (Avg merge 14d 3h) (305 merged PRs in 30d)

Description

Request Description

Support for aten::tensordot in OpenVINO would enhance compatibility with PyTorch models by enabling tensor contraction through matrix multiplication followed by summation over specified axes. This operation is essential for various machine learning and numerical computing applications.

Feature Use Case

The tensordot operation is widely used in deep learning for tasks such as attention mechanisms, tensor decompositions, and high-dimensional matrix multiplications. Adding this functionality would improve inference optimization and ensure better integration with models requiring aten::tensordot.

Issue submission checklist

  • The feature request or improvement must be related to OpenVINO

Contributor guide

Research direction
Study existing aten operation implementations in OpenVINO source (e.g., aten::matmul, aten::bmm) and the PyTorch aten::tensordot specification. Identify required shape inference and kernel logic.
Tech stack
python
Domain
ai
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
C++ programmingOpenVINO operation architecturePyTorch operator semantics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60