-
Notifications
You must be signed in to change notification settings - Fork 697
Add int4mm test to the CUDA CI flow #15181
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/15181
Note: Links to docs will display an error until the docs builds have been completed. ❌ 2 New Failures, 1 Unrelated FailureAs of commit 45cbb84 with merge base 11c0b4f ( NEW FAILURES - The following jobs have failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
See inline, thank you @desertfire
.github/workflows/cuda.yml
Outdated
| optimum-cli export executorch \ | ||
| --model "mistralai/Voxtral-Mini-3B-2507" \ | ||
| --task "multimodal-text-to-text" \ | ||
| --recipe "cuda" \ | ||
| --dtype bfloat16 \ | ||
| --device cuda \ | ||
| --max_seq_len 1024 \ | ||
| --qlinear 4w \ | ||
| --qlinear_encoder 4w \ | ||
| --qlinear_packing_format tile_packed_to_4d \ | ||
| --qlinear_encoder_packing_format tile_packed_to_4d \ | ||
| --output_dir ./ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Can you update the README.md file with this instructions?
https://github.com/pytorch/executorch/blob/main/examples/models/voxtral/README.md#cuda-support
2. Update models/voxtral/READEME.md with CUDA quantization
examples/models/voxtral/README.md
Outdated
| --max_seq_len 1024 \ | ||
| --qlinear 4w \ | ||
| --qlinear_encoder 4w \ | ||
| --qembedding 4w \ |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
if you're removing from CI, don't forget to update here as well
Tested in CI