Add CUDA memory optimization for long-context GQA attention #26658
+201
−1
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
This commit introduces memory management improvements to reduce fragmentation and workspace spikes in CUDA attention operations, particularly for long-context Group Query Attention (GQA). Changes: - Add AttentionMemoryPlanner for shape-aware buffer reuse - Implement bucket allocation (256KB) in CUDAAllocator - Add predictive workspace clamping (512MB limit) - Add AttentionMemOpt graph transformer skeleton - Add unit tests for memory planner Addresses issue microsoft#25965
Author
|
@microsoft-github-policy-service agree |
Author
|
@microsoft-github-policy-service agree
…On Tue, Nov 25, 2025 at 11:05 PM microsoft-github-policy-service[bot] < ***@***.***> wrote:
*microsoft-github-policy-service[bot]* left a comment
(microsoft/onnxruntime#26658)
<#26658 (comment)>
@cafeTechne <https://github.com/cafeTechne> please read the following
Contributor License Agreement(CLA). If you agree with the CLA, please reply
with the following information.
@microsoft-github-policy-service agree [company="{your company}"]
Options:
- (default - no company specified) I have sole ownership of
intellectual property rights to my Submissions and I am not making
Submissions in the course of work for my employer.
@microsoft-github-policy-service agree
- (when company given) I am making Submissions in the course of work
for my employer (or my employer has intellectual property rights in my
Submissions by contract or applicable law). I have permission from my
employer to make Submissions and enter into this Agreement on behalf of my
employer. By signing below, the defined term “You” includes me and my
employer.
@microsoft-github-policy-service agree company="Microsoft"
Contributor License Agreement Contribution License Agreement
This Contribution License Agreement (*“Agreement”*) is agreed to by the
party signing below (*“You”*),
and conveys certain license rights to Microsoft Corporation and its
affiliates (“Microsoft”) for Your
contributions to Microsoft open source projects. This Agreement is
effective as of the latest signature
date below.
1. *Definitions*.
*“Code”* means the computer software code, whether in human-readable
or machine-executable form,
that is delivered by You to Microsoft under this Agreement.
*“Project”* means any of the projects owned or managed by Microsoft
and offered under a license
approved by the Open Source Initiative (www.opensource.org).
*“Submit”* is the act of uploading, submitting, transmitting, or
distributing code or other content to any
Project, including but not limited to communication on electronic
mailing lists, source code control
systems, and issue tracking systems that are managed by, or on behalf
of, the Project for the purpose of
discussing and improving that Project, but excluding communication
that is conspicuously marked or
otherwise designated in writing by You as “Not a Submission.”
*“Submission”* means the Code and any other copyrightable material
Submitted by You, including any
associated comments and documentation.
2. *Your Submission*. You must agree to the terms of this Agreement
before making a Submission to any
Project. This Agreement covers any and all Submissions that You, now
or in the future (except as
described in Section 4 below), Submit to any Project.
3. *Originality of Work*. You represent that each of Your Submissions
is entirely Your original work.
Should You wish to Submit materials that are not Your original work,
You may Submit them separately
to the Project if You (a) retain all copyright and license information
that was in the materials as You
received them, (b) in the description accompanying Your Submission,
include the phrase “Submission
containing materials of a third party:” followed by the names of the
third party and any licenses or other
restrictions of which You are aware, and (c) follow any other
instructions in the Project’s written
guidelines concerning Submissions.
4. *Your Employer*. References to “employer” in this Agreement include
Your employer or anyone else
for whom You are acting in making Your Submission, e.g. as a
contractor, vendor, or agent. If Your
Submission is made in the course of Your work for an employer or Your
employer has intellectual
property rights in Your Submission by contract or applicable law, You
must secure permission from Your
employer to make the Submission before signing this Agreement. In that
case, the term “You” in this
Agreement will refer to You and the employer collectively. If You
change employers in the future and
desire to Submit additional Submissions for the new employer, then You
agree to sign a new Agreement
and secure permission from the new employer before Submitting those
Submissions.
5. *Licenses*.
- *Copyright License*. You grant Microsoft, and those who receive the
Submission directly or
indirectly from Microsoft, a perpetual, worldwide, non-exclusive,
royalty-free, irrevocable license in the
Submission to reproduce, prepare derivative works of, publicly
display, publicly perform, and distribute
the Submission and such derivative works, and to sublicense any or all
of the foregoing rights to third
parties.
- *Patent License*. You grant Microsoft, and those who receive the
Submission directly or
indirectly from Microsoft, a perpetual, worldwide, non-exclusive,
royalty-free, irrevocable license under
Your patent claims that are necessarily infringed by the Submission or
the combination of the
Submission with the Project to which it was Submitted to make, have
made, use, offer to sell, sell and
import or otherwise dispose of the Submission alone or with the
Project.
- *Other Rights Reserved*. Each party reserves all rights not
expressly granted in this Agreement.
No additional licenses or rights whatsoever (including, without
limitation, any implied licenses) are
granted by implication, exhaustion, estoppel or otherwise.
6. *Representations and Warranties*. You represent that You are
legally entitled to grant the above
licenses. You represent that each of Your Submissions is entirely Your
original work (except as You may
have disclosed under Section 3). You represent that You have secured
permission from Your employer to
make the Submission in cases where Your Submission is made in the
course of Your work for Your
employer or Your employer has intellectual property rights in Your
Submission by contract or applicable
law. If You are signing this Agreement on behalf of Your employer, You
represent and warrant that You
have the necessary authority to bind the listed employer to the
obligations contained in this Agreement.
You are not expected to provide support for Your Submission, unless
You choose to do so. UNLESS
REQUIRED BY APPLICABLE LAW OR AGREED TO IN WRITING, AND EXCEPT FOR THE
WARRANTIES
EXPRESSLY STATED IN SECTIONS 3, 4, AND 6, THE SUBMISSION PROVIDED
UNDER THIS AGREEMENT IS
PROVIDED WITHOUT WARRANTY OF ANY KIND, INCLUDING, BUT NOT LIMITED TO,
ANY WARRANTY OF
NONINFRINGEMENT, MERCHANTABILITY, OR FITNESS FOR A PARTICULAR PURPOSE.
7. *Notice to Microsoft*. You agree to notify Microsoft in writing of
any facts or circumstances of which
You later become aware that would make Your representations in this
Agreement inaccurate in any
respect.
8. *Information about Submissions*. You agree that contributions to
Projects and information about
contributions may be maintained indefinitely and disclosed publicly,
including Your name and other
information that You submit with Your Submission.
9. *Governing Law/Jurisdiction*. This Agreement is governed by the
laws of the State of Washington, and
the parties consent to exclusive jurisdiction and venue in the federal
courts sitting in King County,
Washington, unless no federal subject matter jurisdiction exists, in
which case the parties consent to
exclusive jurisdiction and venue in the Superior Court of King County,
Washington. The parties waive all
defenses of lack of personal jurisdiction and forum non-conveniens.
10. *Entire Agreement/Assignment*. This Agreement is the entire
agreement between the parties, and
supersedes any and all prior agreements, understandings or
communications, written or oral, between
the parties relating to the subject matter hereof. This Agreement may
be assigned by Microsoft.
—
Reply to this email directly, view it on GitHub
<#26658 (comment)>,
or unsubscribe
<https://github.com/notifications/unsubscribe-auth/AFACJ5QNPD7DKFAKFYIKVRL36TOEJAVCNFSM6AAAAACNGJN5NWVHI2DSMVQWIX3LMV43OSLTON2WKQ3PNVWWK3TUHMZTKNZXHE3DGNZWGA>
.
You are receiving this because you were mentioned.Message ID:
***@***.***>
|
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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
This PR introduces memory management improvements to the CUDA execution provider that reduce fragmentation, excessive workspace growth, and peak-memory spikes observed during long-context Group Query Attention (GQA) inference.
Fixes #25965
Motivation
Issue #25965 reports OOM failures when running long-sequence models (4k–16k tokens) on CUDA EP. Root causes identified:
These issues are particularly problematic for:
Changes
1. Attention Memory Planner (
onnxruntime/core/providers/cuda/transformers/)New files:
attention_memory_planner.hattention_memory_planner.ccFeatures:
2. CUDA Allocator Improvements (
onnxruntime/core/providers/cuda/cuda_allocator.cc)Modified:
CUDAAllocator::Alloc()now rounds all allocations to 256KB buckets3. Graph Optimization Pass (
onnxruntime/core/optimizer/)New files:
attention_memopt.hattention_memopt.ccPurpose:
4. Testing (
onnxruntime/test/providers/cuda/)New file:
attention_mem_tests.ccCoverage:
AttentionMemoryPlannerHeuristics Implemented
H1: Bucket Allocations
Round all CUDA allocations to nearest 256KB to reduce fragmentation.
H2: Predictive Workspace Clamping
limit = min(512MB, predicted_size * 1.25, user_configured_cap)H3: Tensor Lifetime Reuse
If two intermediates have identical shapes and non-overlapping lifetimes → reuse buffer.
H4: GQA Path Fusion (Skeleton)
Framework for reusing KV expansion buffers across attention blocks.
Impact
Expected improvements (based on analysis of issue #25965):
Compatibility
Testing Strategy
Unit Tests
attention_mem_tests.ccvalidates planner logicIntegration Testing
Performance Validation
Future Work
AttentionMemoryPlannerin attention opsChecklist
Notes for Reviewers
Scope: This PR provides the foundation for memory optimization. Full integration with attention kernels is intentionally deferred to keep the PR focused and reviewable.
Conservative approach: All heuristics use safe defaults and don't change existing behavior unless memory pressure is detected.
Testing limitation: Author has AMD GPU (RX 6500 XT), so full CUDA testing relies on CI infrastructure.
Design rationale: The bucket allocation and workspace clamping are based on analysis of TensorRT and PyTorch's memory management strategies for similar workloads.