Decode cudaErrorIllegalAddress
Open
Nobody has claimed this yet.
bug
- Dominant language
- Jupyter Notebook
- Stars
- 159
- Forks
- 22
- PR merge metrics
- No merged PRs in 30d
Description
Version
0.4.0
Describe the bug.
In our Triton Inference Server service, we need to decode JPEG images in each request. After the service has been running for a period of time (a few days), we encounter the cudaErrorIllegalAddress error.
I checked the VRAM usage, it's using about 3GB in total of 15GB.
Minimum reproducible example
Environment details
Relevant log output
Other/Misc.
No response
Check for duplicates
- I have searched the open bugs/issues and have found no duplicates for this bug report
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
No source files, tests, or runnable reproduction are provided. Start by reproducing JPEG decoding in the Triton Inference Server service and collect the missing environment and CUDA log details; done means the illegal-address failure is isolated to a reproducible scenario with a confirmed resolution.
Written by the indexing model from the issue text.
Assessment
- Domain
- computer-vision
- Issue type
- Bug
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100