fix: Add more protection around backend response APIs to avoid crashing server from improper API use by backends #367
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
rmccorm4
changed the title
Tabrizian
approved these changes
Jun 6, 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Outdated suggestions cannot be applied.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.
Related PR: triton-inference-server/backend#99
Previously, some backends like the
identity_backendwould callTRITONBACKEND_Response*APIs even when it had anullptrresponse, leading to server segfaults. While the backend can be improved to not do this, a more holistic approach for all backends is to catch this in core and gracefully return an error.NOTE: There are likely more APIs that could be checked/improved, but keeping scope small to what APIs were involved in the L0_pinned_memory failures.