[Fix][cuDNN] Avoid thread-local workspace pool for ConvEntry - #20362
Merged
Merged
Conversation
tqchen
requested changes
Sep 16, 2026
PengYoun9
force-pushed
the
fix_cudnn_cleanworkspace
branch
from
September 16, 2026 12:58
e0af088 to
5c2ff6b
Compare
PengYoun9
changed the title
tqchen
approved these changes
Sep 16, 2026
PengYoun9
force-pushed
the
fix_cudnn_cleanworkspace
branch
from
September 17, 2026 02:17
5c2ff6b to
48e02a8
Compare
PengYoun9
changed the title
…20361) Use AllocDataSpace and FreeDataSpace instead of AllocWorkspace and FreeWorkspace for cuDNN convolution workspace allocation. This avoids the lifetime dependency on the thread-local workspace pool during process teardown and fixes the shutdown crash.
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fix a core dump during process shutdown when using CUDA contrib operators.
The issue is caused by the CUDA thread-local workspace pool being destroyed
before contrib thread-local objects that still retain workspace.
Initialize the workspace pool when the CUDA device API is requested so that
it remains valid when retained workspace is released during thread teardown.
Fixes #20361