Tensor-parallel DeepSeek V4 Flash inference on dual AMD Strix Halo over OdinLink USB4/TB5 RDMA or Mellanox RoCE v2.
☆23Sep 20, 2026Updated last month
Alternatives and similar repositories for ds4-strix-halo-tp-odinlink
Users that are interested in ds4-strix-halo-tp-odinlink are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Docker Compose for llama.cpp GGUF servers on AMD Strix Halo: Qwen, Gemma, and Laguna packages (abliterated and quantized), stock Vulkan p…☆27Aug 17, 2026Updated 2 months ago
- Portable optimized ROCm and Qwen3.8-27B setup for AMD Strix Halo☆83Sep 16, 2026Updated last month
- Immutable alternatives to built-in array operators☆12Aug 29, 2016Updated 10 years ago
- Code for the culip ("CUda for Linear and Integer Programming") project, containing GPU primitives for linear algebra, linear optimization…☆19Oct 12, 2018Updated 8 years ago
- Skripte zur Aufbereitung der DFS AIP☆11Sep 28, 2025Updated last year
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- CMP 170HX technical wiki: silicon, firmware, the community unlock, procedures and open problems. 55 pages.☆73Aug 22, 2026Updated last month
- An inference framework customized for AI MAX 395, compatible with both Linux and Windows, and supports deploying only qwen3.8-flash-next.…☆101Updated this week
- experimental linux kernel modules and userspace drivers for RDMA-over-usb4/thunderbolt on consumer hardware☆71Updated this week
- ☆20Aug 28, 2026Updated last month
- Winning Qwen and DeepSeek setups for AMD Strix Halo: pinned Ansible recipes and matched benchmarks on a 128 GiB Ryzen AI Max+ 395 / Radeo…☆22Oct 6, 2026Updated 2 weeks ago
- LLM inference in C/C++☆26Oct 8, 2026Updated last week
- Qubic Lite Reference Implementation (ql-node software)☆10Sep 22, 2018Updated 8 years ago
- High-performance Lemonade alternative for AMD Strix Halo & Radeon — latest MoE models (Ling-3.0-Flash, Qwen 3.8 Flash Next, Ornith 1.5), …☆90Sep 24, 2026Updated 3 weeks ago
- MAchine Guided Energy Efficient Compilation Framework and GCC Plugin☆13May 3, 2017Updated 9 years 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.
- ⚡️ WebExtension Vite+React Starter Template☆10May 24, 2023Updated 3 years ago
- Near-optimal vector quantization from Google's ICLR 2026 paper — 95% recall, 5x compression, zero preprocessing, pure Python FAISS replac…☆20Mar 28, 2026Updated 6 months ago
- Enable/disable skills from loading into pi context at startup☆24Apr 28, 2026Updated 5 months ago
- Strata fork: Qwen3.8-Flash-Next 125B MoE in NVFP4 on one RTX 20-50 card (12 GB+) and 64 GB of RAM or more. Setup installs our GPTQ quants…☆178Updated this week
- Reasoning model integration for pydantic-ai's agent☆15Oct 13, 2025Updated last year
- Wireless interface to ChatGPT using speech-to-text and text-to-speech, all through OpenAI APIs, running on an ESP32.☆14Apr 7, 2025Updated last year
- Lua "back-end" for BIND with dlz_dlopen()☆10Dec 10, 2011Updated 14 years ago
- Some reverse engineering for an Android calculator using AllWinner A50.☆17Dec 9, 2022Updated 3 years ago
- Create dnsmasq DHCP & DNS configs using the Netbox API.☆14Jul 25, 2023Updated 3 years ago
- Bare Metal GPUs on DigitalOcean Gradient AI • AdPurpose-built for serious AI teams training foundational models, running large-scale inference, and pushing the boundaries of what's possible.
- 瑞数☆14Feb 18, 2024Updated 2 years ago
- A powerful & efficient browser agent that automates any task on the web☆24Aug 28, 2026Updated last month
- Malice VirusTotal Plugin☆12Feb 24, 2019Updated 7 years ago
- Simulate touch events with a mouse, for fun and profit.☆15Mar 13, 2012Updated 14 years ago
- Implement LLVM passes in python☆11Feb 2, 2025Updated last year
- Private, local-first AI "life OS": any model per life-domain over a markdown vault on your machine. Council mode, open source (GPL-3.0).☆35Oct 11, 2026Updated last week
- An OpenSource Homebrew's Store☆12Oct 12, 2013Updated 13 years ago
- An automated pipeline to convert e-books into beautifully illustrated scenes using local AI backends ComfyUI and SD Forge.☆11Jan 9, 2026Updated 9 months ago
- The fastest way to run Qwen3.8-Flash-Next on Strix Halo (gfx1151)☆1,018Updated this week
- 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.
- ☆14Sep 23, 2016Updated 10 years ago
- Research paper collection management plugin for Claude Code, Codex CLI, and Gemini CLI☆33Aug 24, 2026Updated last month
- Open Source Hardware Repository for the Sourccey Robot☆28Oct 1, 2026Updated 2 weeks ago
- ☆14Jan 12, 2024Updated 2 years ago
- NeonGoby alias analysis checker☆14Dec 21, 2015Updated 10 years ago
- Salt integration of CheckMK☆13Oct 22, 2021Updated 4 years ago
- Salt Formula for Prometheus monitoring☆10Jan 1, 2021Updated 5 years ago