Add Diode Inductor max-autotune benchmarks to gemm, addmm, bmm#758
Open
jananisriram wants to merge 1 commit intomainfrom
Open
Add Diode Inductor max-autotune benchmarks to gemm, addmm, bmm#758jananisriram wants to merge 1 commit intomainfrom
jananisriram wants to merge 1 commit intomainfrom
Conversation
jananisriram
had a problem deploying
to
docker-s3-upload
GitHub Actions
Error
jananisriram
had a problem deploying
to
docker-s3-upload
GitHub Actions
Error
jananisriram
had a problem deploying
to
docker-s3-upload
GitHub Actions
Error
|
@jananisriram has exported this pull request. If you are a Meta employee, you can view the originating Diff in D89398916. |
Summary: Add Inductor max-autotune benchmarking using Diode to TritonBench for the `gemm`, `addmm`, and `bmm` operators. This diff reduces friction in verifying Diode results against the base max-autotune results. NOTE: The TritonBench benchmark currently includes the overhead of setting up and tearing down Diode within the benchmark, i.e. metrics like tflops and latency. Actual Diode benchmarking numbers should be slightly better than what TritonBench reports. Differential Revision: D89398916
facebook-github-bot
force-pushed
the
export-D89398916
branch
from
cdcb2bd to
1d7e3db
Compare
facebook-github-bot
had a problem deploying
to
docker-s3-upload
GitHub Actions
Failure
facebook-github-bot
had a problem deploying
to
docker-s3-upload
GitHub Actions
Failure
facebook-github-bot
had a problem deploying
to
docker-s3-upload
GitHub Actions
Failure
NikhilAPatel
approved these changes
Dec 23, 2025
| @@ -0,0 +1,44 @@ | |||
| """Diode (ML model for pruning autotuning configs) utils for TritonBench operators.""" | |||
|
|
|||
| import diode.torch_diode.config as diode_config | |||
Contributor
There was a problem hiding this comment.
Might wanna try the with try_import("HAS_DIODE"): pattern here. https://github.com/meta-pytorch/tritonbench/blob/main/tritonbench/operators/gemm/operator.py#L34
Contributor
There was a problem hiding this comment.
Yeah second Nikhil here, diode will not always exist in OSS env and this will cause issues.
xuzhao9
approved these changes
Dec 23, 2025
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 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.
Summary:
Add Inductor max-autotune benchmarking using Diode to TritonBench for the
gemm,addmm, andbmmoperators. This diff reduces friction in verifying Diode results against the base max-autotune results.NOTE: The TritonBench benchmark currently includes the overhead of setting up and tearing down Diode within the benchmark, i.e. metrics like tflops and latency. Actual Diode benchmarking numbers should be slightly better than what TritonBench reports.
Differential Revision: D89398916