Use vllm-bench to benchmark OpenAI-compatible or vLLM serving endpoints, especially multi-turn chat load tests. Use when the user asks for vllm bench, vllm-bench, multi-turn benchmark, chat serving benchmark, TTFT/TPOT/throughput measurement, concurrency…
Profile GPU workloads with NVIDIA Nsight Systems (nsys). Use this skill when the user says 'profile', 'nsys', 'capture a trace', 'GPU profiling', 'kernel breakdown', 'where is time spent', 'decode is slow', 'prefill is slow', 'TPOT regression', 'TTFT…
Use vllm-bench to benchmark OpenAI-compatible or vLLM serving endpoints, especially multi-turn chat load tests. Use when the user asks for vllm bench, vllm-bench, multi-turn benchmark, chat serving benchmark, TTFT/TPOT/throughput measurement, concurrency…
Track any non-trivial task through a doc placed in the right domain directory under docs/ (models/<line>/, subsystems/<area>/, playbooks/, lessons/, etc.). Covers the full lifecycle: read docs first, write a plan, wait for approval, log execution, and capture…