8000 try relanding cublaslt autotuning support for TunableOp # by bilal2vec · Pull Request #153316 · pytorch/pytorch · GitHub
[go: up one dir, main page]
Skip to content

try relanding cublaslt autotuning support for TunableOp # #153316

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
Draft
wants to merge 22 commits into
base: main
Choose a base branch
from
Draft

try relanding cublaslt autotuning support for TunableOp # #153316

wants to merge 22 commits into from

Conversation

bilal2vec
Copy link
Contributor
@bilal2vec bilal2vec commented May 10, 2025 •
edited
Loading

Try relanding #133896

Adds support for cublaslt autotuning to TunableOp.

Todo:

  • Add and test ScaledGemmTunableOp
  • Benchmarking numbers

bilal2vec and others added 22 commits September 4, 2024 16:39
@bilal2vec @pytorchmergebot
cublaslt autotuning support for TunableOp
3a6e60f
@bilal2vec @pytorchmergebot
add scaledgemm support
6ec4b12
@bilal2vec @pytorchmergebot
enable autotuned scaledgemm for cuda
260c276
@bilal2vec @pytorchmergebot
add support for more fp8 dtypes (req for pytorch/cublaslt support) an…
15e4b5d 
…d fix fp8 dDesc issue
@bilal2vec @pytorchmergebot
address comments and lint
08bcd64
@bilal2vec @pytorchmergebot
add tunable gemm_and_bias
4d06095
@bilal2vec @pytorchmergebot
replace elifdef with elif defined to pass rocm tests
278a82c
@bilal2vec @pytorchmergebot
fix gemm_add_and_bias
62ea661
@bilal2vec @pytorchmergebot
edit
0316c3d
@bilal2vec @pytorchmergebot
dispatch to cuda/rocm-specific fp8 types
676b872
@bilal2vec @pytorchmergebot
fix dispatching
85391c5
@bilal2vec @pytorchmergebot
fix descriptors for bmm and scaled gemm
02a110b
@bilal2vec @pytorchmergebot
add missing changes from last commit
99cc728
@bilal2vec @pytorchmergebot
fix dispatching to fp8 dtypes for cuda/rocm
6e555e8
@bilal2vec @pytorchmergebot
lint
ce341d0
@jeffdaily
Merge branch 'main' into bilal/cublas_tuning
cccd381
@bilal2vec
undo to fix windows macro
14fa00b
@bilal2vec
remove ifdef inside argument list
2a5d7a9
@bilal2vec
fix typo
68a55f8
@bilal2vec
fix rocm datatype typo
ba332f0
@bilal2vec
lint
c0fe674
@bilal2vec
Merge branch 'main' into bilal/cublas_tuning
945b27e
@pytorch-bot PyTorch Bot
Copy link
pytorch-bot bot commented May 10, 2025 •
edited
Loading

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/153316

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

❌ 1 New Failure

As of commit 945b27e with merge base b5f1345 (image):

NEW FAILURE - The following job has failed:

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

@pytorch-bot pytorch-bot bot added the ci-no-td Do not run TD on this PR label May 10, 2025
@github-actions GitHub Actions
Copy link
Contributor

This PR needs a release notes: label

If your changes are user facing and intended to be a part of release notes, please use a label starting with release notes:.

If not, please add the topic: not user facing label.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "topic: not user facing"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@eqy eqy Awaiting requested review from eqy eqy will be requested when the pull request is marked ready for review eqy is a code owner

@syed-ahmed syed-ahmed Awaiting requested review from syed-ahmed syed-ahmed will be requested when the pull request is marked ready for review syed-ahmed is a code owner

Assignees
No one assigned
Labels
ci-no-td Do not run TD on this PR open source
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@bilal2vec @pytorchbot @jeffdaily
0