float8: remove unneeded kernel for scale generation #616
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
|
Stack from ghstack (oldest at bottom): |
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/ao/616
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit bb3106d with merge base 8bba8ed ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
facebook-github-bot
added
the
CLA Signed
vkuzo
added a commit
that referenced
this pull request
Aug 6, 2024
Summary: The code to create a float8 scale is unnecessarily creating an extra GPU kernel launch by calling `torch.empty`, removing this. Test Plan: ``` // extract trace of a linear fwd+bwd with python benchmarks/float8/profile_linear_float8.py ~/local/tmp/test // verify that the GPU kernel creating an empty scale tensor is no longer there // unit tests pass ./test/float8/test_everything.sh ``` Reviewers: Subscribers: Tasks: Tags: ghstack-source-id: 8be2b5d ghstack-comment-id: 2272205849 Pull Request resolved: #616
vkuzo
commented
Aug 6, 2024
y-sq
approved these changes
Aug 6, 2024
drisspg
approved these changes
Aug 6, 2024
drisspg
reviewed
Aug 6, 2024
jainapurva
pushed a commit
that referenced
this pull request
Aug 7, 2024
Summary: The code to create a float8 scale is unnecessarily creating an extra GPU kernel launch by calling `torch.empty`, removing this. There is no performance impact, but it does make things easier to debug by reducing log size / making GPU traces simpler. Test Plan: ``` // extract trace of a linear fwd+bwd with python benchmarks/float8/profile_linear_float8.py ~/local/tmp/test // verify that the GPU kernel creating an empty scale tensor is no longer there // unit tests pass ./test/float8/test_everything.sh ``` Reviewers: Subscribers: Tasks: Tags:
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Summary:
The code to create a float8 scale is unnecessarily creating an extra GPU
kernel launch by calling
torch.empty, removing this.There is no performance impact, but it does make things easier to debug by reducing log size / making GPU traces simpler.
Test Plan:
Reviewers:
Subscribers:
Tasks:
Tags: