Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, unified memory pressure, thermal risk, Docker/runtime issues, and validates vLLM/Ollama/llama.cpp/SGLang recipes.

Headless 4K remote desktop for the NVIDIA DGX Spark (GB10): one-command installer for Sunshine + Moonlight low-latency game streaming with NVENC hardware encoding, a software virtual display (no HDMI dummy plug), GDM autologin, and optional Tailscale.

Turn any NVIDIA GPU into a local AI platform. Inference + fine-tuning in your browser. One command to start, automatic clustering.

Serve GLM-5.2 469B (REAP-pruned, NVFP4) across 3× NVIDIA DGX Spark with vLLM pipeline parallelism — 256K context, production-ready config and patches

Ubuntu 24.04 + NVIDIA stack setup guide for GB10 / DGX Spark systems

Complete setup guide for a 2-node NVIDIA DGX Spark cluster — distributed training, CUDA inference with EXO, NCCL tuning for Grace Blackwell, NVMe-TCP shared storage, and 200 Gb/s direct fabric networking.

Practical AI homelab setup guides for GB10, Mac Studio Ultra, RoCE/RDMA, MikroTik switching, NCCL, and heterogeneous workload experiments.

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

Real-time monitoring dashboard for NVIDIA DGX Spark / Dell Pro Max GB10 clusters — FastAPI + WebSocket + SQLite, with vLLM inference integration

Pre-built PyTorch wheels and build scripts for NVIDIA DGX Spark (GB10, sm_121, Blackwell, CUDA 13.0, ARM64)

NXO — Distributed AI inference for NVIDIA/Linux. Fork of EXO focused on CUDA, tinygrad, and DGX Spark clusters.

Real, reproducible LLM inference benchmarks on the NVIDIA DGX Spark — parallel agent sessions, tok/s and latency under load, with an interactive dashboard and one-command recipes

DeepSeek-V4-Flash DSpark speculative decoding on 2x DGX Spark (GB10/sm_121), 1M context — our fp8 recipe + independent reproduction and cross-build benchmarks of the NVFP4-KV build. Honest, apples-to-apples measurements.

Deploy DeepSeek-V4-Flash on dual-node DGX Spark with DSpark speculative decoding, vLLM, and a 1M-token context length using the nvfp4_ds_mla KV-cache path.

Production-ready local AI agent stack for NVIDIA DGX Spark / ASUS GB10. Gemma 4 31B NVFP4 + bge-m3 embeddings + OpenClaw gateway, one docker compose up.

Reproducible, hardened vLLM serving kit for nvidia/Qwen3.6-35B-A3B-NVFP4 on the NVIDIA DGX Spark (GB10 Grace Blackwell, SM121): OpenAI-compatible, MTP speculative decoding, tool-calling, plus eval + metrics helpers.