graphsignal-profiler
GPU inference profiling, tracing, and performance monitoring
All Skills in This Repository (1)
Pure Emerald Level IndicatorsFrequently Asked Questions
FAQPage SchemaHow to install Graphsignal Profiler?โผ
Run `npx skills add graphsignal/graphsignal-profiler --all -g -y` in your terminal to install this skill globally.
How to profile a vLLM or SGLang server?โผ
Set your GRAPHSIGNAL_API_KEY environment variable, then prefix your launch command with `graphsignal-run`, for example `graphsignal-run vllm serve <model> --port 8000`.
Does Graphsignal slow down production inference?โผ
No. GPU activity is collected through low-overhead CUPTI APIs, and all analysis and uploading happens in a separate sidecar process.
Can I profile PyTorch scripts without changing code?โผ
Yes. Run your script with `graphsignal-run python my_app.py`, or call `graphsignal.watch()` once at startup before any CUDA work begins.
Does Graphsignal record prompts or completions?โผ
No. It only sends performance metrics and traces to api.graphsignal.com over outbound connections; prompt and completion content is never recorded.
Related Repositories in Software Engineering
View All in Software Engineeringโopenclaw
Run a personal AI assistant across your devices and chat apps
superpowers
Gives coding agents a disciplined workflow from idea to merged code
react
AI agent skills for building, testing, and porting React core