Reject out-of-range HTTP JSON tensor values#8821
Open
fallintoplace wants to merge 1 commit into
Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 adds explicit range checks while parsing HTTP JSON tensor data for narrow integer datatypes. Values that cannot be represented by the requested tensor datatype are now rejected instead of being narrowed with a C++ cast.
The affected cases are
UINT8,UINT16,UINT32,INT8,INT16, andINT32.Why
The HTTP JSON parser currently reads numeric JSON values into
uint64_torint64_tand then casts into the tensor element type. For values like256on aUINT8input, that silently changes the value before it reaches the backend. Signed narrow casts can also produce implementation-defined results.Tests
git diff --check -- src/http_server.cc qa/L0_infer/infer_test.pypython3 -m py_compile qa/L0_infer/infer_test.pyI could not run the full
qa/L0_inferflow locally because it requires the Triton QA server/model runtime.