Set up the Graphsignal Profiler for inference workloads — vLLM, SGLang, PyTorch, and dstack services. Use when the user wants GPU profiling, tracing, or monitoring for inference, asks about graphsignal-run or graphsignal.watch(), or asks about CUPTI / Prometheus / OTLP setup.
$npx -y skills add graphsignal/graphsignal-profiler --skill graphsignal-profilerInstalls into the current project.
Run `npx skills use "https://github.com/graphsignal/graphsignal-profiler" --skill "graphsignal/graphsignal-profiler"` and follow the generated skill instructions now. Read its complete output, redirecting it to a temporary file first if necessary. Resolve relative paths from the supporting-files directory it provides.
Use the skills in "https://github.com/graphsignal/graphsignal-profiler" that are relevant to the current task. Run `npx skills add "https://github.com/graphsignal/graphsignal-profiler"` and select the relevant skills, then follow their instructions.