Skip to content

Update llama cmake for custom ops #10176

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

Merged
merged 1 commit into from
Apr 15, 2025
Merged

Update llama cmake for custom ops #10176

merged 1 commit into from
Apr 15, 2025

Conversation

lucylq
Copy link
Contributor

@lucylq lucylq commented Apr 14, 2025

Fix #10166

target_link_options_shared_lib has different behavior for macos and other platforms; seems like whole-archive was causing issues.

Test Plan
sh .ci/scripts/test_llama_torchao_lowbit.sh
https://github.com/pytorch/executorch/blob/main/examples/models/llama/README.md#running-with-low-bit-kernels

Copy link

pytorch-bot bot commented Apr 14, 2025

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/10176

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

❌ 1 New Failure

As of commit 55cf2ad with merge base 2ed44ce (image):

NEW FAILURE - The following job has failed:

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 Apr 14, 2025
@lucylq lucylq marked this pull request as ready for review April 14, 2025 23:52
@lucylq lucylq requested a review from jackzhxng as a code owner April 14, 2025 23:52
@lucylq lucylq requested a review from metascroy April 14, 2025 23:52
@lucylq lucylq added the release notes: build Changes related to build, including dependency upgrades, build flags, optimizations, etc. label Apr 14, 2025
@@ -427,7 +427,7 @@ cmake -DPYTHON_EXECUTABLE=python \
-DEXECUTORCH_BUILD_EXTENSION_DATA_LOADER=ON \
-DEXECUTORCH_BUILD_EXTENSION_MODULE=ON \
-DEXECUTORCH_BUILD_EXTENSION_TENSOR=ON \
-DEXECUTORCH_BUILD_XNNPACK=ON \
-DEXECUTORCH_BUILD_XNNPACK=OFF \
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

update this to match the ci script.

@lucylq
Copy link
Contributor Author

lucylq commented Apr 14, 2025

self-reminder to CP.

@lucylq lucylq merged commit 5809428 into main Apr 15, 2025
173 of 175 checks passed
@lucylq lucylq deleted the lfq.llama-cmake branch April 15, 2025 16:10
@lucylq
Copy link
Contributor Author

lucylq commented Apr 15, 2025

@pytorchbot cherry-pick --onto release/0.6 -c fix

Copy link

pytorch-bot bot commented Apr 15, 2025

❌ 🤖 pytorchbot command failed:

@pytorchbot cherry-pick: error: argument -c/--classification: invalid choice: 'fix' (choose from 'regression', 'critical', 'fixnewfeature', 'docs', 'release')

usage: @pytorchbot cherry-pick --onto ONTO [--fixes FIXES] -c
                               {regression,critical,fixnewfeature,docs,release}

Try @pytorchbot --help for more info.

@lucylq
Copy link
Contributor Author

lucylq commented Apr 15, 2025

@pytorchbot cherry-pick --onto release/0.6 -c critical

pytorchbot pushed a commit that referenced this pull request Apr 15, 2025
Fix #10166

target_link_options_shared_lib has different behavior for macos and
other platforms; seems like whole-archive was causing issues.

Test Plan
`sh .ci/scripts/test_llama_torchao_lowbit.sh`

https://github.com/pytorch/executorch/blob/main/examples/models/llama/README.md#running-with-low-bit-kernels
(cherry picked from commit 5809428)
@pytorchbot
Copy link
Collaborator

Cherry picking #10176

The cherry pick PR is at #10201 and it is recommended to link a critical cherry pick PR with an issue. The following tracker issues are updated:

Details for Dev Infra team Raised by workflow job

keyprocedure pushed a commit to keyprocedure/executorch that referenced this pull request Apr 21, 2025
Fix pytorch#10166

target_link_options_shared_lib has different behavior for macos and
other platforms; seems like whole-archive was causing issues.

Test Plan
`sh .ci/scripts/test_llama_torchao_lowbit.sh`

https://github.com/pytorch/executorch/blob/main/examples/models/llama/README.md#running-with-low-bit-kernels
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
ciflow/trunk CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. release notes: build Changes related to build, including dependency upgrades, build flags, optimizations, etc.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

Release 0.6 llama low-bit kernels
4 participants