Unsupported model family or non-llm: "whisper-v3"
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 1.9k
- Forks
- 152
- Avg merge
- 4h 14m
- Merged PRs (30d)
- 11
Description
I use Ubuntu 26.04 on a Strix Halo, with FLM v0.9.46. When I run flm serve whisper-v3:turbo, I get the following:
[FLM] Using environment-specified port: 52625
[ERROR] Unsupported model family or non-llm: "whisper-v3"
[FLM] Loading model: /home/laurent/.config/flm/models/Llama-3.2-1B-NPU2
[FLM] Starting server on port 52625...
[FLM] WebServer started on port 52625 with 10 I/O threads
[FLM] Press Ctrl+C to stop.
Note: We cannot open issues on the new https://github.com/ROCm/FastFlowLM repo. Is that a bug or a feature?
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by tracing the model-family validation reached by flm serve whisper-v3:turbo and determine whether Whisper models are intended to be supported. Check the handling of whisper-v3 and the serve path for non-LLM models; done means the command no longer reports the model family as unsupported and behaves as documented.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- ai
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Mostly clear
- Newbie friendliness
- 42/100