fix: use integer dtype for random_seed in query script#722
Open
andrewwhitecdw wants to merge 1 commit into
Open
fix: use integer dtype for random_seed in query script#722andrewwhitecdw wants to merge 1 commit into
andrewwhitecdw wants to merge 1 commit into
Conversation
The standalone query script passed random_seed as np.single (float), but the Triton input spec and the streaming variant use np.int_. This could cause type mismatches when the model expects an integer seed. Adds a unit test that mocks pytriton and verifies the dtype is np.int_. Signed-off-by: Andrew White <andrewh@cdw.com>
andrewwhitecdw
requested review from
athitten,
meatybobby,
oyilmaz-nvidia and
pthombre
as code owners
July 24, 2026 14:30
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Bug
The standalone
scripts/deploy/nlp/query.pyscript passedrandom_seedasnp.single(float), but the Triton input spec and the streaming variant usenp.int_. This could cause type mismatches when the model expects an integer seed.Fix
Use
np.int_for therandom_seedinput array.Test
Added
tests/unit_tests/deploy/test_query_script.py::TestQueryLLMInputs::test_random_seed_uses_int_dtype, which mockspytriton.clientand verifies the seed array uses integer dtype.Verification
ruff check scripts/deploy/nlp/query.py tests/unit_tests/deploy/test_query_script.pyandruff format --check ...pass.