Add workspace estimation accounting and reporting - #31962
Draft
Chi Lo (chilo-ms) wants to merge 6 commits into
Draft
Add workspace estimation accounting and reporting#31962Chi Lo (chilo-ms) wants to merge 6 commits into
Chi Lo (chilo-ms) wants to merge 6 commits into
Conversation
Move workspace reporting out of GetCapabilityForEP and into the completed GraphPartitioner::Partition boundary. Track workspace estimates as pending during capability probing and commit them only for nodes that ORT actually assigns. Replace the generic safety-margin workspace with the MatMulNBits Level-1 estimate before CUDA's budget decision. Preserve workspace estimates across the layout-transformation deferred-commit path, and report non-workspace, workspace, and total estimated memory once per resource-accounted EP. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: cdd38fe6-fcf3-45c2-acea-b8e6206a7839
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: cdd38fe6-fcf3-45c2-acea-b8e6206a7839
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: cdd38fe6-fcf3-45c2-acea-b8e6206a7839
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: cdd38fe6-fcf3-45c2-acea-b8e6206a7839
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: cdd38fe6-fcf3-45c2-acea-b8e6206a7839
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: cdd38fe6-fcf3-45c2-acea-b8e6206a7839
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Description
Adds workspace-memory accounting and reporting for resource-constrained graph partitioning.
GetCapabilityand commits it only for accepted nodesmax(profile, estimator)when both exist, and fallback when neither is availableMatMulNBitsworkspace estimator before CUDA budget decisionsSizeBasedResourceAccountantto reflect that it handles profile, fallback, and operator-estimated costsRelated to #29775.
Testing
Added resource-accountant and two-pass partitioning unit coverage. Tests were not run for this update.