graphsignal

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.

Fetch Graphsignal signal context via the graphsignal-context CLI. Use when the user needs signal context, time-range queries for signals/profiles/errors, signal guide content, or CLI access to the context APIs.