An explorable 3D city that shows how Postgres actually works

The fastest, litest AI Gateway. Rust core with Python SDK. Call 100+ LLM APIs in OpenAI (or native) format with cost tracking, guardrails, load balancing, and logging [Bedrock, Azure, OpenAI, Anthr…

Universal document viewer for the web — open-source, framework-agnostic viewer powered by a built-from-scratch WebAssembly engine for high-fidelity rendering across PDF, DOCX, PPTX, and images.

Headless terminal for AI agents, automation, and CI — allowing them to drive real interactive TUI and CLI programs while also letting other agents or humans observe.

bluetooth mesh chat, IRC vibes

A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations

Pure Rust Inference Engine

Source code for the Microsoft Comic Chat IRC client

Import OpenStreetMap data into a PostgreSQL/PostGIS database

Library for shoehorning the Slug text/graphics GPU rendering library into projects.

GLM-5.2 Quantrio INT4/INT8 Mixed Abliterated — SPEED=1 C1≈30 tok/s @ 128k on 4x DGX Spark. Step-by-step recipe, image bake, results.

Postgres rewritten in Rust, now passing 100% of the Postgres regression tests

Run GLM-5.2 (744B MoE) on a 25GB-RAM consumer machine — pure C, zero deps, experts streamed from disk. Tiny engine, immense model. 🐦

Open Source search based on OpenStreetMap data

MiniMax-M3 (428B, no pruning) at 36 tok/s on 2× NVIDIA DGX Spark — W4A16 GPTQ + NVFP4 KV + EAGLE-3 speculative decoding on vLLM. Three serving lanes: speed / balanced / long-context.

DeepSeek V4 Flash DSpark 1M NVFP4 KV recipe for 2x DGX Spark

Docker configuration for running VLLM on dual DGX Sparks

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.

MiMo-V2.5 Omni TP=2 on 2x DGX Spark · 1M context · NVFP4 4-bit KV (~1.97M-token KV pool @ 1M, ~30 tok/s) · 69-eval: thinking-OFF 97.8 beats thinking-ON 90.6 for tool/agent work

turn qwen 3.6 27B-> AR -> diffusion (opendllm + d3llm)

A Docker-based pipeline for fine-tuning FLUX.1-dev with LoRA on the DGX Spark

NVIDIA DGX Spark Playbooks

This is the official code of the paper "A Multi-Agent System Enables Versatile Information Extraction from the Chemical Literature"

This is the official code of the paper "MolNexTR: a generalized deep learning model for molecular image recognition"

MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.

Convert PDF to markdown + JSON quickly with high accuracy

Unlimited OCR Works: Welcome the Era of One-shot Long-horizon Parsing.

DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

advanced compilers