Fix DML regression from allocator refactor and enable unrounded weight allocation in ORT API#17030
Merged
Fix DML regression from allocator refactor and enable unrounded weight allocation in ORT API#17030
Conversation
…t allocations through ORT API
PatriceVignola
previously approved these changes
Aug 7, 2023
smk2007
previously approved these changes
Aug 7, 2023
Contributor
|
To merge this PR I suggest reverting the "apply lintrunner" commit, then manually remove the trailing spaces on this line:
|
jeffbloo
force-pushed
the
user/jeffbloo/DmlAllocFix
branch
from
9eddebb to
1bee33d
Compare
justinchuby
approved these changes
Aug 10, 2023
jchen351
pushed a commit
that referenced
this pull request
Aug 12, 2023
…t allocation in ORT API (#17030) This addresses a DML performance regression from the following PR resulting in allocations not being rounded and pooled in the DML execution provider. #15833 This also fixes a pre-existing limitation that allocations during session initialization (primarily large weights and persistent resources) only bypassed rounding and pooling while using the Winml API. The allocator now also respects a caller's rounding mode parameter when provided.
Contributor
kleiti
pushed a commit
to kleiti/onnxruntime
that referenced
this pull request
Mar 22, 2024
…t allocation in ORT API (microsoft#17030) This addresses a DML performance regression from the following PR resulting in allocations not being rounded and pooled in the DML execution provider. microsoft#15833 This also fixes a pre-existing limitation that allocations during session initialization (primarily large weights and persistent resources) only bypassed rounding and pooling while using the Winml API. The allocator now also respects a caller's rounding mode parameter when provided.
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
4 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.
This addresses a DML performance regression from the following PR resulting in allocations not being rounded and pooled in the DML execution provider.
#15833
This also fixes a pre-existing limitation that allocations during session initialization (primarily large weights and persistent resources) only bypassed rounding and pooling while using the Winml API. The allocator now also respects a caller's rounding mode parameter when provided.