Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can ORT version 1.16.3 support Moe? #19159

Open
chuanxiangWei opened this issue Jan 16, 2024 · 2 comments
Open

Can ORT version 1.16.3 support Moe? #19159

chuanxiangWei opened this issue Jan 16, 2024 · 2 comments
Labels
ep:CUDA issues related to the CUDA execution provider stale issues that have not been addressed in a while; categorized by a bot

Comments

@chuanxiangWei
Copy link

Describe the issue

The documentation(https://github.com/microsoft/onnxruntime/blob/main/docs/ContribOperators.md) tells me Ort supports Moe. I installed the 1.16.3 version of onnxruntime-gpu through pip. But when calling the InferenceSession function, ORT error: com.microsoft:MoE(-1) is not a registered functionc/op. Doesn't the 1.16.3 version of ORT support Moe yet?

To reproduce

None

Urgency

No response

Platform

Linux

OS Version

CentOS Linux release 7.9.2009

ONNX Runtime Installation

Released Package

ONNX Runtime Version or Commit ID

1.16.3

ONNX Runtime API

Python

Architecture

X64

Execution Provider

CUDA

Execution Provider Library Version

cuda 11.4

@github-actions github-actions bot added the ep:CUDA issues related to the CUDA execution provider label Jan 16, 2024
@chuanxiangWei
Copy link
Author

I suddenly found that only master branch supported moe, tag 1.16.3 doesn't support. Yes?

Copy link
Contributor

This issue has been automatically marked as stale due to inactivity and will be closed in 30 days if no further activity occurs. If further support is needed, please provide an update and/or more details.

@github-actions github-actions bot added the stale issues that have not been addressed in a while; categorized by a bot label Feb 16, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ep:CUDA issues related to the CUDA execution provider stale issues that have not been addressed in a while; categorized by a bot
Projects
None yet
Development

No branches or pull requests

1 participant