microsoft / microsoft/foundry-dev-tools

Errors loading and downloading models

Open
#207 5 comments 0 reactions 1 assignee View on GitHub

@jiaxuwu2021 is already working on this.

Since May 22, 2025.

Dominant language
JavaScript
Stars
2.1k
Forks
260
Avg merge
42m
Merged PRs (30d)
29

Description

Hi!
I'm getting following warning and error messages in console/logs after using first few models

...
[2025-05-21T08:45:15.067Z] [INFO] Information: WorkspaceAutomation.Catalog.HuggingFaceClientProvider [0]  2025-05-21T10:45:10.5540621+02:00 Download for model Uri:microsoft/Phi-3.5-vision-instruct-onnx completed.

[2025-05-21T08:45:15.075Z] [ERROR] The configuration file C:\Users\...\.aitk\models\my-models.yml has been modified by other process. Please try again. 

Models worked at first, when I downloaded one, ignoring the error above - most probably it happened because I was downloading two models at once.

But then with second model downloaded it got broken completely:

[2025-05-21T09:09:21.457Z] [ERROR] Unable to call the Phi-3-vision-128k-gpu-int4-rtn-block-32-onnx inference endpoint .  Please check if the input or configuration is correct. Connection error. 
[2025-05-21T09:09:21.457Z] [ERROR] Failed to chatStream. model = "ONNX/Phi-3-vision-128k-gpu-int4-rtn-block-32-onnx", errorMessage = "Error: Unable to call the Phi-3-vision-128k-gpu-int4-rtn-block-32-onnx inference endpoint .  Please check if the input or configuration is correct.", errorType = "c", errorObject = {"innerError":{"cause":{"message":"request to http://localhost:5272/v1/chat/completions failed, reason: ","type":"system","errno":"ECONNREFUSED","code":"ECONNREFUSED"}}} 
[2025-05-21T09:09:21.536Z] [ERROR] Failed to chatStream. model = "ONNX/Phi-3-vision-128k-gpu-int4-rtn-block-32-onnx", errorMessage = "Error: Unable to call the Phi-3-vision-128k-gpu-int4-rtn-block-32-onnx inference endpoint .  Please check if the input or configuration is correct.", errorType = "c", errorObject = {"innerError":{"cause":{"message":"request to http://localhost:5272/v1/chat/completions failed, reason: ","type":"system","errno":"ECONNREFUSED","code":"ECONNREFUSED"}}} 
[2025-05-21T09:09:21.537Z] [ERROR] Unable to call the Phi-3-vision-128k-gpu-int4-rtn-block-32-onnx inference endpoint .  Please check if the input or configuration is correct. Connection error. 
[2025-05-21T09:23:41.997Z] [WARNING] Failed to get loaded models
[2025-05-21T09:23:42.149Z] [WARNING] Failed to get downloaded models
[2025-05-21T09:23:42.880Z] [ERROR]  
[2025-05-21T09:31:43.862Z] [WARNING] Failed to get loaded models

Deleting contents of "C:\Users....aitk" doesn't help.
Possible issue... I was running Foundy Local in my terminal next to this... and it seems that when I stopped the foundry service (foundry service stop) it started working. Maybe interfering port?

Thanks!

Contributor guide

No contributing guide indexed for this repository

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.