dgx-spark

Pure Rust Inference Engine

sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems

Fully uncensored, capability-enhanced abliteration of Qwen3.6-27B. NVFP4 + z-lab DFlash speculative decoding (n=12) on the unified ghcr.io/aeon-7/aeon-vllm-ultimate:latest container, tuned for long-context draft acceptance on DGX Spark. 6 HF variants (BF16/NVFP4/MTP/MTP-XS), docker-compose, and QuickStart.

Qwen3.5-122B-A10B on DGX Spark: 28.3 → 51 tok/s (+80%)

One-command vLLM installation for NVIDIA DGX Spark with Blackwell GB10 GPUs (sm_121 architecture)

Local diagnostic CLI for NVIDIA DGX Spark (GB10). Detects power caps, UMA pressure, thermal risk, CUDA 13/SM_121 wheel mismatches, Docker issues, and validates vLLM/Ollama/llama.cpp/SGLang recipes.

Reproducible refusal-subspace editing and TP=2 deployment of DeepSeek V4 Flash 0731 on two DGX Sparks

Two-node DGX Spark/ASUS GX10 DeepSeek V4 Flash DSpark NVFP4 port for vLLM 0.25, with live dashboard and reproducible deployment.

DGX Spark / GB10 vLLM Docker stack for large-model serving, presets, patches, and validation notes.

DFlash vLLM for DGX Spark — Plug & Play Block-Diffusion Speculative Decoding

Bleeding edge vLLM Docker image for the NVIDIA DGX Spark (GB10 / sm_121a).

Legacy: self-hosted LLM/RAG stack installer for DGX Spark (arm64). The work continued as AGmind Systems Lab — measured local-LLM performance evidence (Strix Halo, DGX Spark, llama.cpp, vLLM): https://agmind.ai

GLM-5.2 (744B/40B MoE) on a 4× DGX Spark / GB10 (sm_121) cluster: portable Triton sparse-MLA kernels, a data-free expert prune, MTP draft, and a one-script bootstrap.

Plug-and-play, dependency-free web command center for DGX Spark fleets (and any GPU boxes): live per-node GPU/CPU/mem/temps/power, optional RouterOS switch monitoring, and per-model decode/prefill/TTFT/KV cards. Point it at your own hardware.

Production-grade recipe for DeepSeek-V4-Flash-0731 (284B MoE) on 2x NVIDIA DGX Spark: self-healing 2-node vLLM cluster, reboot-verified, tuned DSpark speculative decoding (~75 tok/s), full benchmarks, OpenAI Codex CLI integration

LLM fine-tuning with LoRA + NVFP4/MXFP8 on NVIDIA DGX Spark (Blackwell GB10)

Serve Poolside Laguna S 2.1 (NVFP4) on the NVIDIA DGX Spark (GB10) without hanging your box. Working stack, crash-safe configs, benchmarks, and the exact gotchas.

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

GLM-5.2 744B with a true 4-bit NVFP4 KV cache on 4x DGX Spark: 42 tok/s peak, 317K-token KV pool (+58.6% vs fp8), needle-verified at 250K depth, serving 316K context

Run DeepSeek-V4-Flash 304B on a single NVIDIA GB10 / DGX Spark - 2-bit MoE planes, FP4 quality recovery, speculative decoding