{"slug":"openlair-tensorrt-llm","source_name":"openlair/tensorrt-llm","name":"Openlair/Tensorrt LLM","description":"Optimizes LLM inference with NVIDIA TensorRT for maximum throughput and lowest latency. Use for production deployment on NVIDIA GPUs (A100/H100), when you need 10-100x faster inference than PyTorch, or for serving models with quantization (FP8/INT4), in-flight batching, and multi-GPU scaling.","version":1,"lift":{"pass_rate_delta_pts":18.18,"pass_rate_pct":90.9,"total_cases":22,"passed_cases":20,"tokens_delta_pct":33.3,"turns_delta_pct":0,"verdict":"mixed","benchmark_model":"gemini-3.6-flash","grading_method":"judged","completed_at":"2026-08-07T19:19:34.041619+00:00"},"skill_score":0.9091,"benchmark_models":[{"model":"gemini-3.6-flash","headline":true,"delta_pts":18.18,"with_pass_pct":90.9,"without_pass_pct":72.7,"tokens_delta_pct":33.3,"turns_delta_pct":0,"total_cases":22,"cases_aggregated":22,"verdict":"mixed","never_hurt":true,"completed_at":"2026-08-07T19:19:34.041619+00:00","run_id":"7821175c-2936-4e51-b008-6e36b3631b1b","version_number":1,"is_latest_version":true,"gate":null}],"trust":{"skill_safety":"passed","safety_status":"clean","intent_verdict":"safe","content_status":"clean","indexable":true},"license":"MIT","install_count":0,"manifest_hash":"b6310a15382013bce9bc78b93f4ef180a9dca9b3f49faf2f054681ac12a4fa1d","raw_url":"https://app.decimal.ai/s/openlair-tensorrt-llm/SKILL.md","scorecard_url":"https://app.decimal.ai/skills/openlair-tensorrt-llm"}