Add TRT-LLM support to serving-config and fix HTTP probe

[anandhu-eng]

• parse.py: fix duplicate _SGLANG_PATTERNS/_choose_patterns definitions; add _TRTLLM_PATTERNS matching real LLM Args dump format; update _choose_patterns and _detect_framework for TRT-LLM; add "trtllm" to argparse choices
• run.sh: document valid --serving-framework values (auto|vllm|sglang|trtllm)
• customize.py: replace broken /server_info TRT-LLM probe with /perf_metrics (unique to TRT-LLM); vLLM and SGLang detection order unchanged

🧾 PR Checklist

• Target branch is dev

📌 Note: PRs must be raised against dev. Do not commit directly to main.

📁 File Hygiene & Output Handling

• No unintended files (e.g., logs, cache, temp files, pycache, output folders) are committed

📝 Comments & Communication

• Proper inline comments are added to explain important or non-obvious changes
• PR title and description clearly state what the PR does and why
• Related issues (if any) are properly referenced (Fixes #, Related to #, etc.)

🛡️ Safety & Security

• No secrets or credentials are committed
• Paths, shell commands, and environment handling are safe and portable

[github-actions]

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