ROCmForge

Local AMD GPU LLM inference engine (HIP/ROCm) — quantized GGUF, Q4_0/K-quants, flash attention, KV cache. ~515 tok/s decode on Qwen2.5-0.5B Q4_0 (RX 7900 XT).

amd

View on GitHub

3 Stars

2 Forks

0 Watchers

Rust Language

gpl-3.0 License

51.6 SrcLog Score

Cost to Build

$5.36M

Market Value

$5.05M

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 ROCmForge

Question copied to clipboard

What is the oldnordic/ROCmForge GitHub project? Description: "Local AMD GPU LLM inference engine (HIP/ROCm) — quantized GGUF, Q4_0/K-quants, flash attention, KV cache. ~515 tok/s decode on Qwen2.5-0.5B Q4_0 (RX 7900 XT).". Written in Rust. 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 ROCmForge

Clone via HTTPS

git clone https://github.com/oldnordic/ROCmForge.git

Clone via SSH

[email protected]:oldnordic/ROCmForge.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the ROCmForge issue tracker:

Open GitHub Issues

Similar to ROCmForge

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