OpenMOSS / OpenMOSS/AnyGPT

CUDA Runtime Error: Device-Side Assert Triggered

Open
#49 0 comments 3 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
882
Forks
76
PR merge metrics
No merged PRs in 30d

Description

I encountered a RuntimeError: CUDA error: device-side assert triggered while running the inference on the base model. Example prompt: text|image|A bustling medieval market scene with vendors selling exotic goods under colorful tents

Below is a screenshot of the error.

Image

I tried setting the environment variable CUDA_LAUNCH_BLOCKING=1 as suggested, but the error persisted. Could this be related to an input format issue or a problem with model compatibility on CUDA?

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

No source file or test is identified in the report. Start by reproducing base-model inference with the example prompt and inspect the input format and CUDA traceback; done means the prompt runs without the device-side assert or the model/input incompatibility is documented.

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
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.