F

fw16-ai-inference

Project information

Dual-GPU AMD local LLM fleet: llama.cpp routers with measured memory safety (fit-check guard, freeze mode), LocalAI media lanes, Bifrost gateway. Built on Framework 16 with Ryzen 9 7940HS w/ Radeon 780M iGPU + RX 7700S dGPU. Vulkan and ROCm 7.1

llama.cpp AMD vulkan local-llm self-hosted-ai localai bifrost

47 Commits
1 Branch
0 Tags

README
Apache License 2.0

Created on

September 21, 2026

Loading