-
Notifications
You must be signed in to change notification settings - Fork 2.8k
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.
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
[CUDA] Attention kernel provider option #21344
Merged
Merged
Conversation
This file contains 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
@@ -0,0 +1,70 @@ | |||
// Copyright (c) Microsoft Corporation. All rights reserved. |
Check warning
Code scanning / lintrunner
CLANGFORMAT/format Warning
See https://clang.llvm.org/docs/ClangFormat.html.
Run lintrunner -a to apply this patch.
Run lintrunner -a to apply this patch.
@@ -0,0 +1,149 @@ | |||
// Copyright (c) Microsoft Corporation. All rights reserved. |
Check warning
Code scanning / lintrunner
CLANGFORMAT/format Warning
See https://clang.llvm.org/docs/ClangFormat.html.
Run lintrunner -a to apply this patch.
Run lintrunner -a to apply this patch.
kunal-vaishnavi
previously approved these changes
Jul 18, 2024
wangyems
approved these changes
Jul 19, 2024
kunal-vaishnavi
approved these changes
Jul 19, 2024
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Outdated suggestions cannot be applied.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.
Description
sdpa_kernel
to choose which attention kernel to run for testing purpose.CUDA provider option sdpa_kernel
Instead of setting environment variable, we also support setting it in provider option. Note that the setting is global per session. That could help performance testing of each kernel.
Attention Kernel Debug Info
Set an environment variable
ORT_ENABLE_ATTENTION_KERNEL_DEBUG_INFO=1
, and ORT will print sdpa kernel used in each node:For example
It will show debug information of kernel used in testing:
In this test case, the debug info shows that one session uses trt fused attention and another session use efficient attention.
Motivation and Context