[TRTLLM-14571][infra] Enable container-local AutoTuner cache in CI

[YihuiLu512]

• Wire TLLM_AUTOTUNER_CACHE_PATH into pytest stages to reuse tactic profiling across testcases via a volatile container-local /tmp path.
• Harden _deserialize_cache_data to skip non-literal tactics (SyntaxError) instead of crashing load_cache, e.g. Fp4QuantTactic IntEnum reprs.
• Add regression test for the skip-on-load behavior.

The goal is to improve GPU utilization during CI runs.

Dev Engineer Review

• Configures pytest CI stages to use a container-local /tmp AutoTuner profiling cache, enabling tactic reuse without affecting host or shared caches.
• Updates cache deserialization to catch SyntaxError, log once, and skip invalid non-literal tactic entries instead of failing the entire cache load.
• The change preserves valid cache entries and avoids reusing stale tactics. Configuration scope and cache path are appropriate for volatile CI containers.
• Adds regression coverage for valid and invalid tactic representations.

QA Engineer Review

• Added test: test_load_cache_skips_non_literal_tactic().
• No corresponding tests/integration/test_lists/ coverage was identified; the test is not listed in CI test-db/ or manual QA qa/ files.
• Verdict: insufficient.

Description

Test Coverage

PR Checklist

Please review the following before submitting your PR:

• PR description clearly explains what and why. If using CodeRabbit's summary, please make sure it makes sense.

• PR Follows TRT-LLM CODING GUIDELINES to the best of your knowledge.

• Test cases are provided for new code paths (see test instructions)

• If PR introduces API changes, an appropriate PR label is added - either api-compatible or api-breaking. For api-breaking, include BREAKING in the PR title.

• Any new dependencies have been scanned for license and vulnerabilities

• CODEOWNERS updated if ownership changes

• Documentation updated as needed

• Update tava architecture diagram if there is a significant design change in PR.

• The reviewers assigned automatically/manually are appropriate for the PR.

• Please check this after reviewing the above items as appropriate for this PR.

GitHub Bot Help

To see a list of available CI bot commands, please comment /bot help.

[YihuiLu512]

/bot run

[coderabbitai]

No actionable comments were generated in the recent review. 🎉

ℹ️ Recent review info

⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Enterprise

Run ID: 5f331fdd-1e5a-40fa-badf-0dd789a48bf6

📥 Commits

Reviewing files that changed from the base of the PR and between 96360f8 and 7600b13.

📒 Files selected for processing (3)

• jenkins/L0_Test.groovy
• tensorrt_llm/_torch/autotuner.py
• tests/unittest/_torch/misc/test_autotuner.py

---

Walkthrough

The PR configures pytest runs to use a container-local AutoTuner profiling cache and updates cache deserialization to skip tactic entries that raise SyntaxError, with a regression test covering valid and invalid entries.

Changes

Autotuner cache reliability

Layer / File(s)	Summary
Container-local cache configuration jenkins/L0_Test.groovy	Pytest commands set TLLM_AUTOTUNER_CACHE_PATH to a volatile /tmp JSON cache path.
Invalid tactic cache handling tensorrt_llm/_torch/autotuner.py, tests/unittest/_torch/misc/test_autotuner.py	Cache loading catches SyntaxError, skips invalid tactic entries, and verifies that valid entries remain loaded.

Estimated code review effort: 2 (Simple) | ~10 minutes

Possibly related PRs

• NVIDIA/TensorRT-LLM#16782: Updates autotuner tactic serialization to avoid literal-evaluation round-trip failures.

Suggested labels: VisualGen

Suggested reviewers: junyixu-nv, asfiyab-nvidia

🚥 Pre-merge checks | ✅ 4 | ❌ 1

❌ Failed checks (1 warning)

Check name	Status	Explanation	Resolution
Description check	⚠️ Warning	The description has useful content, but the required Description and Test Coverage sections are left blank.	Fill in the Description and Test Coverage sections with the problem, the fix, and the tests covering the new behavior.

✅ Passed checks (4 passed)

Check name	Status	Explanation
Title check	✅ Passed	The title matches the PR’s main change and follows the repository’s required [ticket][type] summary format.
Docstring Coverage	✅ Passed	No functions found in the changed files to evaluate docstring coverage. Skipping docstring coverage check.
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.}

[tensorrt-cicd]

PR_Github #61274 [ run ] triggered by Bot. Commit: 7600b13 Link to invocation

[tensorrt-cicd]

PR_Github #61274 [ run ] completed with state FAILURE. Commit: 7600b13
/LLM/main/L0_MergeRequest_PR pipeline #49509 completed with status: 'FAILURE'

CI Report

⚠️ Action Required:

• Please check the failed tests and fix your PR
• If you cannot view the failures, ask the CI triggerer to share details
• Once fixed, request an NVIDIA team member to trigger CI again

CI Agent Failure Analysis

Link to invocation