TurboQuant-Vulkan

TurboQuant-Vulkan

tsuyu122

TurboQuant Vulkan: 3-bit KV cache quantization for llama.cpp using Lloyd-Max Gaussian codebooks. 4.57x compression, Vulkan GPU support (AMD/Intel/NVIDIA). Hobby project.

amd
View on GitHub
3 Stars
0 Forks
3 Watchers
C++ Language
agpl-3.0 License
60.1 SrcLog Score
Cost to Build
$54.3K
Market Value
$47.7K
How is this calculated?

Growth over time

2 data points  ·  2026-04-18 → 2026-04-25
Stars Forks Watchers
💬

How do you feel about this project?

Ask AI about TurboQuant-Vulkan

Question copied to clipboard

What is the tsuyu122/TurboQuant-Vulkan GitHub project? Description: "TurboQuant Vulkan: 3-bit KV cache quantization for llama.cpp using Lloyd-Max Gaussian codebooks. 4.57x compression, Vulkan GPU support (AMD/Intel/NVIDIA). Hobby project.". Written in C++. 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 TurboQuant-Vulkan

Clone via HTTPS

git clone https://github.com/tsuyu122/TurboQuant-Vulkan.git

Clone via SSH

[email protected]:tsuyu122/TurboQuant-Vulkan.git

Download ZIP

Download master.zip

Found an issue?

Report bugs or request features on the TurboQuant-Vulkan issue tracker:

Open GitHub Issues

Similar to TurboQuant-Vulkan

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