Skip to content
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

fix the qnn sdk env issue #7517

Merged
merged 1 commit into from
Jan 7, 2025

Conversation

cccclai
Copy link
Contributor

@cccclai cccclai commented Jan 6, 2025

Summary:
executorch/examples/qualcomm/utils.py will check if QNN_SDK_ROOT is set. This is helpful for oss, but internally we rely on buck to set the deps. Currently we just set QNN_SDK_ROOT to empty to bypass the issue.

buck run mode/dev-nosan //executorch/examples/qualcomm/oss_scripts/llama3_2:llama_qnn -- --compile_only --ptq 16a4w --checkpoint /home/chenlai/local//consolidated.00.pth --params /home/chenlai/local//params.json --tokenizer_model /home/chenlai/local//tokenizer.model --prompt "Once" -m SM8650 --model_size 1B --model_mode hybrid --build_folder /home/chenlai/local   2>&1 | tee static_llama.log

bypass-github-export-checks

Reviewed By: billmguo

Differential Revision: D67814838

Summary:
`executorch/examples/qualcomm/utils.py` will check if `QNN_SDK_ROOT` is set. This is helpful for oss, but internally we rely on buck to set the deps. Currently we just set `QNN_SDK_ROOT` to empty to bypass the issue.

```
buck run mode/dev-nosan //executorch/examples/qualcomm/oss_scripts/llama3_2:llama_qnn -- --compile_only --ptq 16a4w --checkpoint /home/chenlai/local//consolidated.00.pth --params /home/chenlai/local//params.json --tokenizer_model /home/chenlai/local//tokenizer.model --prompt "Once" -m SM8650 --model_size 1B --model_mode hybrid --build_folder /home/chenlai/local   2>&1 | tee static_llama.log
```
bypass-github-export-checks

Reviewed By: billmguo

Differential Revision: D67814838
Copy link

pytorch-bot bot commented Jan 6, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7517

Note: Links to docs will display an error until the docs builds have been completed.

✅ No Failures

As of commit 4a44e09 with merge base 7a2dc47 (image):
💚 Looks good so far! There are no failures yet. 💚

This comment was automatically generated by Dr. CI and updates every 15 minutes.

@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Jan 6, 2025
@facebook-github-bot
Copy link
Contributor

This pull request was exported from Phabricator. Differential Revision: D67814838

@facebook-github-bot facebook-github-bot merged commit 62c6346 into pytorch:main Jan 7, 2025
46 of 49 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. fb-exported topic: not user facing
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants