graphsignal-top: a live view of your inference GPUs

The open-source Graphsignal profiler serves everything it measures as JSON for agents. graphsignal-top is the same data as a live terminal screen: GPU telemetry, engine throughput and latency, and kernels ranked by time, locally or over the network.

CUDA Profiler for Production Inference

Why dev-time CUDA profilers don't fit production inference, and what a profiler built for it looks like: low-overhead kernel attribution, host sync waits, and integrated telemetry.

vLLM Production Observability: From Model to Hardware

Production-grade profiling and monitoring for vLLM: always-on vLLM, PyTorch and CUDA profiling with tracing, metrics and errors in one place.