Add compute unit to coreml llama export #7280
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7280
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit fe7f397 with merge base 8460d42 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
metascroy
added
the
enhancement
|
@pytorchbot label "topic: not user facing" |
metascroy
force-pushed
the
improve-coreml-llm-export-defaults
branch
from
ddac2c7 to
a5eeef0
Compare
YifanShenSZ
approved these changes
Dec 12, 2024
metascroy
force-pushed
the
improve-coreml-llm-export-defaults
branch
from
a5eeef0 to
6592182
Compare
metascroy
force-pushed
the
improve-coreml-llm-export-defaults
branch
from
6592182 to
fe7f397
Compare
cccclai
approved these changes
Dec 15, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This PR adds the option to specify the compute unit when exporting LLMs to CoreML. It also changes the default compute unit to CPU because we observe an 8x speedup on using CPU over GPU for stories110M model on iPhone15, bringing tokens/sec from 14 to 119.