Deep dive into machine learning, computer vision, and software engineering. Expert insights on AI, local LLMs, quantization, and practical implementation details from real-world projects.
An honest roundup of the resources I actually recommend for learning CUDA matrix multiplication optimization — from naive kernels to near-cuBLAS. Compares siboehm, Lei Mao, Salykova, NVIDIA docs, and one of my own deep dives, with explicit guidance on which to read first.
How the three stages of the C++ build pipeline — compilation, linking, and loading — compare, what each one transforms, and which one your build error usually comes from. The pillar guide that ties the three deep-dives together.
How H.264 (AVC), H.265 (HEVC), and AV1 compare on compression efficiency, encoding cost, hardware decode support, patent licensing, and use-case fit. The practical decision matrix for choosing a video codec in 2026.
Step-by-step CUDA matrix multiplication optimization with 9 interactive visualizations. From naive kernels through shared memory tiling to near-cuBLAS speeds.
The definitive reference for every NVIDIA Xid error code: what each means, severity classification, triage flowcharts, and whether you need to fix your code or RMA your GPU.
Deep dive into NVIDIA GPU Xid 31 MMU faults: how GPU virtual memory works, what causes page table walk failures, and how we eliminated 28 daily crashes in a production video pipeline processing 7,000+ videos.