[https://nvbugs/6490028][fix] Bump only the cross-library cublas_tolerance from 1.05 to 1.10 in the test…

[trtllm-agent]

Summary

• Root cause: cublas_tolerance=1.05 on a cross-library ~28us GEMM comparison profiled over only 20 iterations is inside the measurement's own run-to-run noise floor, so the test flakes above threshold by <1% intermittently.
• Fix: Bump only the cross-library cublas_tolerance from 1.05 to 1.10 in the test; keep the intra-CuteDSL 1.05 tolerance unchanged. Added a comment explaining why the two tolerances differ.
• Automated fix generated by repair-bot

Test plan

• Verify fix on the same GPU type as the original failure
• Check for regressions in related tests

Links

• Bug: https://nvbugs/6490028

Dev Engineer Review

• Updated cublas_tolerance from 1.05 to 1.10 only for the cross-library CuteDSL-versus-cuBLASLt comparison.
• Preserved the intra-CuteDSL tolerance at 1.05, with comments documenting the rationale and expected measurement jitter.
• The change is scoped appropriately and introduces no API, configuration, or error-handling changes.

QA Engineer Review

• Modified test: test_cutedsl_nvfp4_heuristic_matches_full_sweep.
• No test-list changes were made. Coverage in test-db/ or qa/ was not identified.
• Verdict: needs follow-up.

[coderabbitai]

Walkthrough

The CuteDSL autotuner test increases the cuBLASLt comparison tolerance from 1.05 to 1.10 and adds comments about cross-library profiling variability.

Changes

Autotuner tolerance adjustment

Layer / File(s)	Summary
Cross-library tolerance validation tests/unittest/_torch/misc/test_autotuner.py	The CuteDSL-versus-cuBLASLt assertion uses a 1.10 tolerance, with comments documenting cross-library and profiling jitter.

Estimated code review effort: 1 (Trivial) | ~2 minutes

Suggested reviewers: peaceh-nv

🚥 Pre-merge checks | ✅ 5

✅ Passed checks (5 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title matches the PR template and clearly describes the tolerance bump for the cross-library test.
Description check	✅ Passed	The description explains the issue, fix, test plan, and bug link, so it is mostly complete despite not using the exact template headings.
Docstring Coverage	✅ Passed	Docstring coverage is 100.00% which is sufficient. The required threshold is 80.00%.
Linked Issues check	✅ Passed	Check skipped because no linked issues were found for this pull request.
Out of Scope Changes check	✅ Passed	Check skipped because no linked issues were found for this pull request.

✨ Finishing Touches

🧪 Generate unit tests (beta)

• Create PR with unit tests

---

_{Comment @coderabbitai help to get the list of available commands.}

[coderabbitai]

Actionable comments posted: 1

🤖 Prompt for all review comments with AI agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

Inline comments:
In `@tests/unittest/_torch/misc/test_autotuner.py`:
- Around line 1263-1267: Register
test_cutedsl_nvfp4_heuristic_matches_full_sweep in both the test-db and qa
test-list registries under tests/integration/test_lists, and add the
corresponding CBTS coverage entry using the repository’s existing conventions so
the test is included in CI and QA routing.

🪄 Autofix (Beta)

Fix all unresolved CodeRabbit comments on this PR:

• Push a commit to this branch (recommended)
• Create a new PR with the fixes

---

ℹ️ Review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: f9ea4ac7-e591-44a6-be38-71ef96ceaa46

📥 Commits

Reviewing files that changed from the base of the PR and between 93efd33 and 75e2cee.

📒 Files selected for processing (1)

• tests/unittest/_torch/misc/test_autotuner.py

[coderabbitai]

📐 Maintainability & Code Quality | 🟡 Minor | ⚡ Quick win

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
set -euo pipefail

test_name='test_cutedsl_nvfp4_heuristic_matches_full_sweep'
for dir in tests/integration/test_lists/test-db tests/integration/test_lists/qa; do
    if [ -d "$dir" ]; then
        rg -n -a "$test_name|test_autotuner.py" "$dir" || true
    fi
done

fd -a 'cbts_touchmap\.sqlite|.*coverage.*' tests || true

Repository: NVIDIA/TensorRT-LLM

Length of output: 293

---

🏁 Script executed:

#!/bin/bash
set -euo pipefail

test_name='test_cutedsl_nvfp4_heuristic_matches_full_sweep'

echo '--- target test definition ---'
rg -n -a "$test_name" tests/unittest/_torch/misc/test_autotuner.py || true

echo '--- test list references ---'
for dir in tests/integration/test_lists/test-db tests/integration/test_lists/qa; do
  if [ -d "$dir" ]; then
    echo "[$dir]"
    rg -n -a "$test_name|test_autotuner.py" "$dir" || true
  fi
done

echo '--- coverage / touchmap artifacts ---'
fd -a 'cbts_touchmap\.sqlite|.*coverage.*' tests || true

Repository: NVIDIA/TensorRT-LLM

Length of output: 535

---

Register test_cutedsl_nvfp4_heuristic_matches_full_sweep in the test lists
It isn’t present in tests/integration/test_lists/test-db/ or tests/integration/test_lists/qa/, and the CBTS coverage artifact is missing here, so this test can slip past CI/QA routing.

🤖 Prompt for AI Agents

Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@tests/unittest/_torch/misc/test_autotuner.py` around lines 1263 - 1267,
Register test_cutedsl_nvfp4_heuristic_matches_full_sweep in both the test-db and
qa test-list registries under tests/integration/test_lists, and add the
corresponding CBTS coverage entry using the repository’s existing conventions so
the test is included in CI and QA routing.

Source: Path instructions