fix: fail fast on endpoint response stalls

[roborluo]

Summary

• add an opt-in generic no-progress watchdog for in-flight endpoint requests
• expose no_progress_timeout_s through YAML and direct CLI aliases
• cancel the watchdog immediately when the active cohort drains, and document TensorRT-LLM disaggregated guidance

Validation

• pytest tests/unit/config/test_schema.py tests/unit/commands/test_benchmark.py tests/unit/load_generator/test_async_session.py -q (334 passed)
• python scripts/regenerate_templates.py --check
• git diff --check
• AGA disaggregated held-response canary: job 537769 failed intentionally after 10s with Endpoint made no response progress for 10.0s with 1 request(s) in flight.

[github-actions]

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

[codecov-commenter]

Codecov Report

❌ Patch coverage is 87.80488% with 10 lines in your changes missing coverage. Please review.
⚠️ Please upload report for BASE (main@ea33275). Learn more about missing BASE report.

Files with missing lines	Patch %	Lines
src/inference_endpoint/load_generator/session.py	87.65%	10 Missing ⚠️

Additional details and impacted files

@@           Coverage Diff           @@
##             main     #462   +/-   ##
=======================================
  Coverage        ?   81.07%           
=======================================
  Files           ?      150           
  Lines           ?    20308           
  Branches        ?        0           
=======================================
  Hits            ?    16464           
  Misses          ?     3844           
  Partials        ?        0           

☔ View full report in Codecov by Harness.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.