NVIDIA/nsight-perf-sdk-for-ai
Always-on, low-overhead GPU and CUDA performance tracing SDK for AI workloads. C++ client APIs, CLI tools, open data model, Perfetto export.
GitHub repository with 112 stars and 6 forks.
Language: CMake
Topics: ai-infrastructure, cpp, cuda, developer-tools, gpu, nvidia, nvtx, observability, perfetto, performance