Auto-graded exercises in low-level ML systems: real C++, real CUDA-C on a software GPU (no NVIDIA hardware), deterministic measured gates.
cpp cuda vscode-extension exercises quantization interview-preparation performance-optimization gpu-programming machine-learning-systems mlsys kv-cache llm learn-cuda llm-inference flash-attention gpu-simulator cuda-exercises auto-graded
-
Updated
Jul 27, 2026 - Python