Skip to content
Skill

graphsignal-profiler

by graphsignal

AI Summary

Graphsignal observes inference workloads from a sidecar process — the profiler. It never shares a process with CUDA: the profiler watches the workload externally via CUPTI, OTLP/gRPC, Prometheus scraping, and NVML. Auto-instrumentation covers vLLM, SGLang, and PyTorch out of the box. Two install pat

Install

Copy this and paste it into Claude Code, Cursor, or any AI assistant:

I want to install the "graphsignal-profiler" skill in my project.

Please run this command in my terminal:
# Install skill into your project
mkdir -p .claude/skills/graphsignal-profiler && curl --retry 3 --retry-delay 2 --retry-all-errors -o .claude/skills/graphsignal-profiler/SKILL.md "https://raw.githubusercontent.com/graphsignal/graphsignal-profiler/main/SKILL.md"

Then restart Claude Code (or reload the window in Cursor) so the skill is picked up.

Description

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.

Graphsignal Profiler

Graphsignal observes inference workloads from a sidecar process — the profiler. It never shares a process with CUDA: the profiler watches the workload externally via CUPTI, OTLP/gRPC, Prometheus scraping, and NVML. Auto-instrumentation covers vLLM, SGLang, and PyTorch out of the box.

Install

Two install patterns depending on how you'll launch the profiler. For graphsignal-run (CLI, recommended): install as a uv tool, isolated from your workload env. `bash UV_TOOL_BIN_DIR=/usr/local/bin uv tool install 'graphsignal[cu12]' # CUDA 12.x

or

UV_TOOL_BIN_DIR=/usr/local/bin uv tool install 'graphsignal[cu13]' # CUDA 13.x ` UV_TOOL_BIN_DIR=/usr/local/bin puts graphsignal-run in a directory that is already on PATH for every shell, including non-interactive scripts and containers. For graphsignal.watch() (in-process Python entry point): install into the app's own env. `bash uv add 'graphsignal[cu12]' # or pip install -U 'graphsignal[cu12]' ` The cu12 / cu13 extras are Linux-only and only needed for GPU profiling.

Configure

The profiler reads its config from environment variables. | Variable | Purpose | | ------------------------------------- | ---------------------------------------------------------------------- | | GRAPHSIGNAL_API_KEY (required) | Account API key. | | GRAPHSIGNAL_API_BASE | Override the API endpoint (defaults to https://api.graphsignal.com). | | GRAPHSIGNAL_TAG_<KEY>=<value> | Arbitrary tag attached to all signals (e.g. GRAPHSIGNAL_TAG_DEPLOYMENT=us-prod). | Set these before invoking graphsignal-run or calling graphsignal.watch().

Discussion

0/2000
Loading comments...

Health Signals

MaintenanceCommitted 1mo ago
Active
Adoption100+ stars on GitHub
241 ★ · Growing
DocsREADME + description
Well-documented

GitHub Signals

Stars241
Forks12
Issues0
Updated1mo ago
View on GitHub
Apache-2.0 License

My Fox Den

Community Rating

Sign in to rate this booster

Works With

Claude Code