Setup turns image reading off for Gemma 4 E4B NPU, which has vision

Open Beginner friendly
  • Is something wrong?
#6,647 2 comments 0 reactions 0 assignees View on GitHub

Maintainers usually reply within 1 day

Nobody has claimed this yet.

Assessment

Difficulty
2/5
Estimated time
1-3 hours
Newbie friendliness
68/100
Issue type
Bug
Clarity
Mostly clear
Activity status
Active
Tech stack
python
Domain
ai

Research direction

Start by tracing first-run setup's image-reading state for gemma-4-e4b-npu and compare it with the model's vision=True registration in MODELS. The issue does not name the setup file or test, so locate those entry points before changing anything. Done means setup reflects the model's vision support and an image question is answered on the NPU.

Written by the indexing model from the issue text.

Description

enhancement npu onboarding p2

When Gemma 4 E4B NPU is chosen in first-run setup, setup marks image reading as unavailable. The model is registered with vision, and FastFlowLM's build serves images, so NPU users lose image reading for no reason.

Done when setup's image-reading state for the NPU model matches what the model supports, with an image question answered on the NPU to prove it.

🔍 Technical details
  • gemma-4-e4b-npu in MODELS has vision=True.
  • Found in the v0.25.4-rc4 desktop test (Windows, embedded Lemonade) while reproducing #6632.
Dominant language
Python
Stars
1.6k
Forks
169
Avg merge
15h 33m
Merged PRs (30d)
832

Getting set up

Open in Codespaces

Starts the project's dev container in your browser, under your own GitHub account.

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.

More from amd/gaia

All issues in amd/gaia

Similar issues

More Python issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.