Unable to run gpt-oss 20b on 32GB machine
Open
Nobody has claimed this yet.
- Dominant language
- C++
- Stars
- 1.9k
- Forks
- 152
- Avg merge
- 4h 14m
- Merged PRs (30d)
- 11
Description
In version 0.9.17 it says:
Improved memory management for gpt-oss:20b. Increase the chance to run on 32GB system (note: NPU can access <50% of total RAM)
However, when testing on my machine, it fails to run with the following error message:
[XRT] ERROR: Failed to submit command to hw queue (0xc01e0200):
Even after the video memory manager split the DMA buffer, the video
memory manager could not page-in all of the required allocations into
video memory at the same time. The device is unable to continue.
FastflowLM version: 0.9.19
Driver version: 32.0.203.314
Total System RAM: 32GB
GPU UMA buffer size: 512MB
NPU accessible Shared memory size: 15.5GB
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 reproducing the failure with FastflowLM 0.9.19, driver 32.0.203.314, 32GB RAM, a 512MB GPU UMA buffer, and 15.5GB of NPU-accessible shared memory. Compare the observed XRT allocation error with the memory-management change described for version 0.9.17. Done means identifying why gpt-oss:20b cannot run on this configuration and either resolving it or documenting the supported limits.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- cpp
- Domain
- ai, embedded-iot
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Quiet
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100