Strix-halo-dual-optimized

Optimized dual AMD Strix Halo (gfx1151) vLLM MoE inference: TP=2 over USB4, tuned int4 MoE kernel, ~8us interconnect, serialized serving

amd

View on GitHub

2 Stars

1 Forks

0 Watchers

Shell Language

mit License

50.1 SrcLog Score

Cost to Build

$500

Market Value

$500

How is this calculated?

Growth over time

1 data points · 2026-07-26 → 2026-07-26

Stars Forks Watchers

💬

How do you feel about this project?

Ask AI about Strix-halo-dual-optimized

Question copied to clipboard

What is the ayysasha/Strix-halo-dual-optimized GitHub project? Description: "Optimized dual AMD Strix Halo (gfx1151) vLLM MoE inference: TP=2 over USB4, tuned int4 MoE kernel, ~8us interconnect, serialized serving". Written in Shell. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

How to clone Strix-halo-dual-optimized

Clone via HTTPS

git clone https://github.com/ayysasha/Strix-halo-dual-optimized.git

Clone via SSH

[email protected]:ayysasha/Strix-halo-dual-optimized.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the Strix-halo-dual-optimized issue tracker:

Open GitHub Issues

Similar to Strix-halo-dual-optimized

webpack madge steal wufuc conditioner awesome-vulkan esl zydis staxrip pyopencl coriander lodjs easytimer.js ocl angular-async-loader node-dependency-tree purge-wrangler require-vuejs GatelessGateSharp SimpleSvm set-egpu parenchyma node-precinct TypeScript-AMD-Boilerplate ScanTree awesome-d3d12 Tensile generator-module-boilerplate akase romania-choropleth