llama.cpp fork optimized for NVIDIA DGX Spark / GB10 (Blackwell, SM 12.1) — TurboQuant weights + KV, NVFP4, DFlash MTP
☆34May 26, 2026Updated 5 months ago
Alternatives and similar repositories for llama.cpp-dgx
Users that are interested in llama.cpp-dgx are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- A small Python library and CLI for working with Cloudflare Turnstile on your own pages - read the sitekey, build the token, verify the re…☆48Oct 12, 2026Updated last month
- Local AI workstation: chat by voice or text, transcribe, generate images and video (with sound on Apple Silicon), benchmark and serve ope…☆26Updated this week
- A local-first AI reading application. Loss-bounded semantic compression with deterministic source traceability. Ingest PDFs/EPUBs and rea…☆30Updated this week
- Operator-grade GPU monitor for NVIDIA GPUs with native GB10 / DGX Spark coherent UMA support — PSI pressure, clock detection, ConnectX-7 …☆37May 31, 2026Updated 5 months ago
- vLLM deployment for Unsloth Qwen3.6-35B-A3B-NVFP4-Fast on NVIDIA DGX Spark☆73Jul 29, 2026Updated 3 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- LLM Stack for nVidia DGX Spark containing LiteLLM, LamaSwap, vLLM, Llama.cpp and ollama☆48Nov 3, 2026Updated 2 weeks ago
- implementation of paint-by-example on comfyui☆11Apr 30, 2026Updated 6 months ago
- Working recipe: MiniMax-M3 NVFP4 at tensor-parallel 3 across 3x DGX Spark (GB10/sm_121) with clean tool-calling. Includes the head-node O…☆16Jul 13, 2026Updated 4 months ago
- FlashQLA TileLang GDN kernels ported to NVIDIA Blackwell consumer (GB10 / DGX Spark)☆18Jun 5, 2026Updated 5 months ago
- Qwen4-Exp (Qwen3.8-Flash-Next) SWA + MTP + PLE-on-iswa — bounded deep-context decode w/ long-range recall, TBQ4 4.25 bpv KV, DSpark + Rot…☆94Sep 24, 2026Updated last month
- 抖音创作者平台全流程运营自动化。支持多账号管理、登录管理、视频/图文/文章发布、互动管理(关注、粉丝、评论、弹幕、私信)、数据分析(账号总览、作品分析、粉丝分析)、创作中心(创作灵感、抖音指数)。使用浏览器自动化模拟真人操作发布内容,浏览器内 API 获取数据。当用户需要运…☆19Apr 2, 2026Updated 7 months ago
- Control DMX512 lights with CSS stylesheets☆11Mar 6, 2018Updated 8 years ago
- English guide + one-command patcher for the vLLM spin-wait bug that overheats NVIDIA DGX Spark / GB10. Credit: nacyot. CPU cores spin at …☆24Aug 17, 2026Updated 3 months ago
- An open source implementation of Microsoft's VALL-E X zero-shot TTS model. Demo is available in https://plachtaa.github.io☆16Apr 18, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- 🤯 Lobe Chat - Warning: Quick and dirty fork to enable lobe-chat to send ComfyUI api request + receive image link + local TTS☆22Nov 1, 2024Updated 2 years ago
- PRT-10255☆13Jun 27, 2025Updated last year
- This suite of nodes unlocks high-performance parallel processing in ComfyUI by utilizing **Model Replication**. Unlike standard offloadin…☆71Aug 13, 2026Updated 3 months ago
- Android Programming☆13Sep 2, 2015Updated 11 years ago
- AIComicX is an AI-powered platform that transforms user-uploaded stories into comics, allowing users to either post their own stories or …☆13Dec 7, 2025Updated 11 months ago
- A Multipurpose toolkit for managing, editing and creating models.☆11Aug 13, 2024Updated 2 years ago
- A wireless bootloader for Arduino and Electric Imp☆11Dec 23, 2014Updated 11 years ago
- Adds controlnet preprocessing feature into Extras tab☆17Jun 12, 2024Updated 2 years ago
- Raspberry PI2 (ARMv7l) port of Webconverger for Digital Signage☆18Nov 15, 2022Updated 4 years ago
- AI Agents on DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- Generates video game music using neural networks.☆10Jun 9, 2022Updated 4 years ago
- LoRA QuickPick is a visual LoRA picker extension for Stable Diffusion WebUI environments.☆14Aug 31, 2026Updated 2 months ago
- Pinned stock Qwen3.8-27B NVFP4 + DFlash2 recipe and measured evidence for one NVIDIA DGX Spark☆21Nov 11, 2026Updated last week
- Absolutely incredible and fresh-pressed Google Colab Notebook to train and generate Music with the SOTA GGA-MG (AR-CNN) Hybrid Neural Net…☆15Oct 2, 2020Updated 6 years ago
- sparkrun - launch, manage, and stop LLM inference workloads on NVIDIA DGX Spark systems. Live support: https://discord.com/invite/GH5kRg…☆567Updated this week
- An open source vector nesting tool☆14Jan 3, 2026Updated 10 months ago
- 一款开源的代码管理工具 - 服务端☆19Oct 20, 2025Updated last year
- Docker configuration for running VLLM on dual DGX Sparks☆2,506Updated this week
- An AI character chat playground with a modern UI☆21Sep 15, 2026Updated 2 months ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- [Exclusive for GitHub] deep-muse: Advanced Text-to-Music Generator Implementation☆17Mar 17, 2022Updated 4 years ago
- Agentic GraphRAG is an open source framework that builds a graph connecting your enterprise knowledge to the conversations your agents ha…☆55Updated this week
- Reproducible Qwen3.8-27B NVFP4 + DFlash2 recipe and qualification evidence for one NVIDIA DGX Spark☆30Aug 21, 2026Updated 3 months ago
- Convert Markdown to PDF using a self-contained Rust binary (CLI or Node.js)☆25Jul 31, 2026Updated 3 months ago
- A research based on artificial Intelligence within Blender, using a custom Nodes Tree Editor☆19Nov 5, 2023Updated 3 years ago
- Stable Diffusion Webui Extension for Civitai, to manage your model much more easily.☆15Feb 11, 2024Updated 2 years ago
- Qwen3.8 Flash at 74 tok/s on a single DGX Spark / GB10. vLLM + MTP recipe, 212 tok/s at 8 streams.☆88Sep 29, 2026Updated last month
Are these results useful?