modelscope / modelscope/DiffSynth-Studio

RuntimeError: Input type (CUDAFloat8_e4m3fnType) and weight type (CPUFloat8_e4m3fnType) should be the same

Open
#821 2 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
13.1k
Forks
1.3k
Avg merge
13h 12m
Merged PRs (30d)
45

Description

Error using qwen image edit low vram RuntimeError: Input type (CUDAFloat8_e4m3fnType) and weight type (CPUFloat8_e4m3fnType) should be the same

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.

Research direction

Start by reproducing the Qwen image edit low-VRAM path described in the issue and trace where the CUDAFloat8_e4m3fnType input meets the CPUFloat8_e4m3fnType weight. Identify the relevant execution entry point from the traceback, then verify the fix with the same low-VRAM scenario; done means the operation runs without the device/type mismatch.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
machine-learning
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
30/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.