8000 Add Vectorized FP8 E4M3 by leslie-fang-intel · Pull Request #152417 · pytorch/pytorch · GitHub
[go: up one dir, main page]
Skip to content

Add Vectorized FP8 E4M3 #152417

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.

Sign up for GitHub

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

Jump to bottom
Open
wants to merge 10 commits into
base: gh/leslie-fang-intel/195/base
Choose a base branch
from
Open

Add Vectorized FP8 E4M3 #152417

wants to merge 10 commits into from

Conversation

leslie-fang-intel
Copy link
Collaborator
@leslie-fang-intel leslie-fang-intel commented Apr 29, 2025 •
edited
Loading

Stack from ghstack (oldest at bottom):

Summary
This PR mainly adding the Vectorized<Float8_e4m3fn> class to support the vectorization of FP8 E4M3 with methods:

  • Convert to/from Vectorized<float>
  • Common vectorized methods like: mul, abs, eq and etc.

Test Plan

./build/bin/vec_test_all_types_AVX512 --gtest_filter=FP8E4M3Test.*

cc @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10 @jerryzh168

@leslie-fang-intel
Update
4c07323 
[ghstack-poisoned]
@pytorch-bot PyTorch Bot
Copy link
pytorch-bot bot commented Apr 29, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/152417

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

❌ 1 New Failure, 1 Unrelated Failure

As of commit 84888d1 with merge base 9608e7f (image):

NEW FAILURE - The following job has failed:

BROKEN TRUNK - The following job failed but were present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

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

@pytorch-bot pytorch-bot bot added the module: cpu CPU specific problem (e.g., perf, algorithm) label Apr 29, 2025
@leslie-fang-intel leslie-fang-intel mentioned this pull request Apr 29, 2025
Open
@leslie-fang-intel leslie-fang-intel marked this pull request as draft April 29, 2025 09:57
@leslie-fang-intel leslie-fang-intel added ciflow/trunk Trigger trunk jobs on your pull request topic: not user facing topic category labels Apr 29, 2025
@leslie-fang-intel
Update
ce07774 
[ghstack-poisoned]
@leslie-fang-intel
Update
6a5f7a2 
[ghstack-poisoned]
@leslie-fang-intel
Update
89bccfa 
[ghstack-poisoned]
@leslie-fang-intel leslie-fang-intel marked this pull request as ready for review April 30, 2025 09:45
@leslie-fang-intel
Update
4b393c3 
[ghstack-poisoned]
jgong5
jgong5 reviewed May 8, 2025
View reviewed changes
Copy link
Collaborator
8000
@jgong5 jgong5 left a comment

Choose a reason for hiding this comment

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

Add UT?

@leslie-fang-intel
Copy link
Collaborator Author

Add UT?

Thanks for the comment. The test case has been added.

@leslie-fang-intel
Update
9faaad4 
[ghstack-poisoned]
mingfeima
mingfeima approved these changes May 9, 2025
View reviewed changes
Copy link
Collaborator
@mingfeima mingfeima left a comment

Choose a reason for hiding this comment

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

Generally LGTM, just the test case needs a little refinement.

One more thing, we don't do E5M2?

@leslie-fang-intel
Update
e8e5cd5 
[ghstack-poisoned]
@leslie-fang-intel
Copy link
Collaborator Author

Generally LGTM, just the test case needs a little refinement.

One more thing, we don't do E5M2?

Thanks for comment. I think we will add E5M2 in next step.

@leslie-fang-intel leslie-fang-intel requested a review from jgong5 May 9, 2025 06:57
@leslie-fang-intel
Update
288b54e 
[ghstack-poisoned]
@leslie-fang-intel
Update
6b87094 
[ghstack-poisoned]
@leslie-fang-intel leslie-fang-intel requested a review from jgong5 May 10, 2025 01:52
@leslie-fang-intel leslie-fang-intel mentioned this pull request May 12, 2025
Open
@leslie-fang-intel leslie-fang-intel mentioned this pull request May 12, 2025
Open
@leslie-fang-intel
Copy link
Collaborator Author

@pytorchbot merge

@pytorchmergebot
Copy link
Collaborator

Merge failed

Reason: Approvers from one of the following sets are needed:

  • superuser (pytorch/metamates)
  • Core Reviewers (mruberry, lezcano, Skylion007, ngimel, peterbell10, ...)
  • Core Maintainers (soumith, gchanan, ezyang, dzhulgakov, malfet, ...)
Details for Dev Infra team Raised by workflow job

Failing merge rule: Core Maintainers

@leslie-fang-intel
Update
84888d1 
[ghstack-poisoned]
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@jgong5 jgong5 jgong5 approved these changes

@mingfeima mingfeima mingfeima approved these changes

@CaoE CaoE CaoE approved these changes

@yanbing-j yanbing-j yanbing-j approved these changes

@vkuzo vkuzo Awaiting requested review from vkuzo

@jerryzh168 jerryzh168 Awaiting requested review from jerryzh168

Assignees
No one assigned
Labels
ciflow/trunk Trigger trunk jobs on your pull request module: cpu CPU specific problem (e.g., perf, algorithm) open source topic: not user facing topic category
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
7 participants
@leslie-fang-intel @pytorchmergebot @jgong5 @mingfeima @CaoE @yanbing-j @pytorchbot
0