Strix Halo local LLM guide: 63-97 t/s direct MoE on Ryzen AI MAX+ 395 / 128GB unified memory. Setup, model choices, benchmarks, and raw evidence.

A CUDA implementation of the transpose-free Quasi-Minimal Residual method

Operator-grade GPU monitor for NVIDIA GPUs with native GB10 / DGX Spark coherent UMA support — PSI pressure, clock detection, ConnectX-7 network layer

Unified Memory Abstraction Layer for AI Inference on AMD APUs and Intel iGPUs

Fundamentals of Accelerated Computing C/C++ is a course provided by NVIDIA.

Local inference server for Apple Silicon — hot-swaps MLX models (LLM, vision, embeddings, TTS, STT) via OpenAI API

Apple Silicon Unified Memory for GPU-Accelerated Analytics — TPC-H benchmarks across DuckDB, NumPy, and MLX

Performance comparison of two different forms of memory management in CUDA

NVML unified memory shim for NVIDIA DGX Spark Grace Blackwell GB10 - enables MAX Engine, PyTorch, and GPU monitoring

Talos-O (Omni): A sovereign, embodied agentic organism forged on AMD Strix Halo. Integrating the Chimera Kernel (Linux 7.0), Zero-Copy Introspection, and the Phronesis Engine. Built from First Principles.

gpu thrashingNVIDIA GPU Unified Memory diagnostic tool — architecture-aware, measurement-based, PCIe/coherent transport detection

GB10-aware CUPTI Activity collector — runtime kind detection, phase management, and JSON output for hardware-coherent UMA platforms

Reproducible Pascal GPU Unified Memory benchmark with Nsight and nvprof profiling

Run LLMs larger than your RAM — native GGUF inference engine with SSD streaming, no GPU required

Empirical kernel scheduling characterization for NVIDIA GB10 (SM121a). Sweeps GEMM tile configurations, classifies PTX instruction paths, captures hardware telemetry

3D U-Net with tf.keras for Large-Model-Support or Unified Memory

Extended the UVM Benchmark such that we can test for huge data workloads(16GiB and more). Needed to make it overflow save and add dataset creation logic for some Applications.

Cycle-accurate UMA fault latency and bandwidth measurement for NVIDIA GPUs. C and PTX. No Python. Pascal (SM 6.0) through Blackwell GB10 (SM 12.1).

NVIDIA GPU validation: PCIe transport, Unified Memory prefetch, SGEMM compute, drift detection.

GB10 unified memory diagnostic suite — bandwidth, contention, atomic coherence, CUPTI activity, power and thermal correlation