llama-swap_homelab

llama-swap config for MTP speculative decoding on AMD RX 7900 XTX (ROCm). Qwen3.6-35B-A3B-MTP and Gemma 4 26B-A4B-MTP with VRAM-tuned context sizing.

amd

View on GitHub

1 Stars

0 Forks

0 Watchers

gpl-3.0 License

30 SrcLog Score

Cost to Build

$2.2K

Market Value

$888

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 llama-swap_homelab

Question copied to clipboard

What is the blockfeed/llama-swap_homelab GitHub project? Description: "llama-swap config for MTP speculative decoding on AMD RX 7900 XTX (ROCm). Qwen3.6-35B-A3B-MTP and Gemma 4 26B-A4B-MTP with VRAM-tuned context sizing.". 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 llama-swap_homelab

Clone via HTTPS

git clone https://github.com/blockfeed/llama-swap_homelab.git

Clone via SSH

[email protected]:blockfeed/llama-swap_homelab.git

Download ZIP

Download main.zip

Found an issue?

Report bugs or request features on the llama-swap_homelab issue tracker:

Open GitHub Issues

Similar to llama-swap_homelab

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