ROCm / ROCm/FastFlowLM

Unsupported model family or non-llm: "whisper-v3"

Open
#651 1 comment 0 reactions 0 assignees View on GitHub

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

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.

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

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.