microsoft / microsoft/winml-cli

feat: add auto into --runtime or alike to auto select best suitable runtime

Open
#1,024 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

enhancement P2 triaged
Dominant language
Python
Stars
40
Forks
11
Avg merge
1d 8h
Merged PRs (30d)
50

Description

It is easy to tell from ort (an onnx file) and ort-genai (a folder with genai_config.json)

As a follow up of https://github.com/microsoft/winml-cli/pull/1015

Folder itself is not enough if we support transformer style inference, it is still using ort not ort-genai

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 reading the runtime-selection work in PR #1015 and the existing --runtime handling. Define the auto-selection behavior for an .ort file versus a folder containing genai_config.json, including transformer-style inference that still uses ort; done means these cases select the suitable runtime.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
cli
Issue type
Feature
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
45/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.