llamacpp-vega-gfx900

llamacpp-vega-gfx900

dhavli

Tuning llama.cpp's Vulkan backend for AMD Vega 56/64 (gfx900/GCN5): 1-bit and MoE inference kernels, multi-GPU layer-split findings, and the dead ends

amd
View on GitHub
3 Stars
0 Forks
0 Watchers
Shell Language
42.1 SrcLog Score
Cost to Build
$5.5K
Market Value
$3.9K
How is this calculated?

Growth over time

2 data points  ·  2026-09-06 → 2026-10-03
Stars Forks Watchers
💬

How do you feel about this project?

Ask AI about llamacpp-vega-gfx900

Question copied to clipboard

What is the dhavli/llamacpp-vega-gfx900 GitHub project? Description: "Tuning llama.cpp's Vulkan backend for AMD Vega 56/64 (gfx900/GCN5): 1-bit and MoE inference kernels, multi-GPU layer-split findings, and the dead ends". 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 llamacpp-vega-gfx900

Clone via HTTPS

git clone https://github.com/dhavli/llamacpp-vega-gfx900.git

Clone via SSH

[email protected]:dhavli/llamacpp-vega-gfx900.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the llamacpp-vega-gfx900 issue tracker:

Open GitHub Issues

Similar to llamacpp-vega-gfx900

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