NVIDIA-NeMo / NVIDIA-NeMo/Export-Deploy

VLM endpoint fails when there are no images in the request

Open
#632 0 comments 0 reactions 1 assignee View on GitHub

@meatybobby is already working on this.

Since Mar 12, 2026.

bug
Dominant language
Python
Stars
42
Forks
18
Avg merge
1d 2h
Merged PRs (30d)
8

Description

Describe the bug

Qwen 2.5 VL deployed with NeMo FW throws an error when it receives a standard chat request with no image data.

Steps/Code to reproduce bug

Send example chat request like the one here

Expected behavior

Endpoint should accept the request and respond with assistant's answer

Additional context

Add any other context about the problem here.

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.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.