Two-rank tensor-parallel LLM serving over USB4v2 between AMD Strix Halo hosts: a custom Linux thunderbolt stream transport, self-healing link, and gufo TP2 integration
☆15Oct 22, 2026Updated 2 weeks ago
Alternatives and similar repositories for strix-dual-exp
Users that are interested in strix-dual-exp are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- llama.cpp modified to work with Strix Halo + dGPU as an accelerator, Dual Strix Halo Machines, or both☆59Updated this week
- 3 MB service that replaces 350 MB of Logi Options+ bloatware. Full haptic motor, force sensor, SmartShift, and button remapping for MX Ma…☆18Mar 25, 2026Updated 7 months ago
- A tool for removing packages and their dependencies on rpm-based systems☆11Jul 26, 2022Updated 4 years ago
- Private extension repository☆11May 25, 2023Updated 3 years ago
- ☆11Updated this week
- 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.
- AI coding agent harness for any hardware, local or cloud (OpenAI-compatible engines). Tuned for AMD Strix Halo: Qwen3.8 125B on the iGPU,…☆37Updated this week
- Flow control nodes for comfyUI, allowing for more diverse workflows☆13Apr 3, 2025Updated last year
- LLM inference engine written from scratch in HIP for AMD Strix Halo (gfx1151) and Qwen3.8-Flash-Next - ~50 tokens/s out to 492k context☆99Updated this week
- Serial port MCP server for Claude Code and other MCP-compatible agents.☆27Mar 7, 2026Updated 8 months ago
- A small library to add Google static maps to your Android app☆10Jan 31, 2013Updated 13 years ago
- ☆12Apr 11, 2026Updated 6 months ago
- An extension for ComyUI that enables saving and loading node presets using the node's context menu☆14May 23, 2024Updated 2 years ago
- Dual accelerometer driver and tablet-mode detection service for Chuwi MiniBook X (N150!)☆11May 12, 2025Updated last year
- llama.cpp fork for GSQ-quantized Qwen3.8-Flash-Next on AMD Strix Halo (gfx1151): faster ROCm prefill, MTP and 4×256K chats with Q8_0 KV a…☆11Oct 11, 2026Updated 3 weeks ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- VigenFlow runs generative diffusion models fully on-device using the AMD Ryzen AI NPU.☆26Updated this week
- Workflow for Java annotation processors☆17Dec 7, 2015Updated 10 years ago
- minimal split keyboard with 34 keys☆11Dec 3, 2022Updated 3 years ago
- A simple solution to audiobook managment☆10Jul 20, 2019Updated 7 years ago
- Control light using a relay.☆11Dec 15, 2020Updated 5 years ago
- rust binding for lean4☆12Jul 1, 2023Updated 3 years ago
- Collection of my nodes for ComyUI☆17Jan 24, 2026Updated 9 months ago
- Connect everything with direct, encrypted WireGuard tunnels. Self-hostable, with no central traffic point.☆25Updated this week
- Attach a debug node to an output to get more information.☆15Jun 14, 2024Updated 2 years ago
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- qwen3.8-flash-next on strix halo — 91g quant, 56 tok/s, 262k context, receipts included☆28Sep 24, 2026Updated last month
- Tools for interfacing with the MetaShunt power profiling tool☆15Feb 3, 2026Updated 9 months ago
- Private web search MCP: SearXNG metasearch → ML reranking → 4-tier fetch cascade (Firecrawl / Crawl4AI / raw / Wayback) with per-domain l…☆24Updated this week
- Pre-driver SM speed-select unlock for Blackwell GB20x (RTX 5090): feasibility, measurement harness, and port research.☆51Oct 24, 2026Updated 2 weeks ago
- Own the code for your OAuth client/provider in as few tokens as possible.☆12Apr 7, 2026Updated 7 months ago
- ComfyUI nodes to use RAVE attention☆13May 22, 2024Updated 2 years ago
- ☆10Jun 6, 2024Updated 2 years ago
- Starter template for SvelteKit + Threlte projects☆12Dec 27, 2022Updated 3 years ago
- Streamable Objects - The 'exec' interface from your DO you're used to, now anywhere☆13Jul 10, 2025Updated last year
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- Program verification with F* course materials☆12Jul 6, 2019Updated 7 years ago
- An easy to use off-policy synthetic data distillation engine for LLMs.☆22Oct 4, 2026Updated last month
- OCaml bindings to the number theory library PARI/GP☆12Jan 11, 2025Updated last year
- Linux microVMs that fork like processes. type-2 hypervisor (VMM) written in Zig. Boot a Linux guest once, snapshot it warm, then fork tha…☆13Oct 22, 2026Updated 2 weeks ago
- GeoServer Docker with GDAL (ECW & MrSID)☆14Feb 25, 2016Updated 10 years ago
- A minimal, certified, executable HTTP server written in Coq☆11Mar 30, 2021Updated 5 years ago
- ☆13Jan 23, 2022Updated 4 years ago