Skip to main content

LLAMA.cpp RPC Test

Notes and some Documentation about my tests with LLAMA.cpp RPC. Using multiple computers for larger inference with multiple GPUs

llama.cpp RPC Multi-GPU Setup Guide (Windows 11 & Linux Distributed Cluster)

This was generated by NOTEBOOKLM from a lot of sources. Question I have three computers at home....

Some Output

Gemma 4 26B A4B - Server llama-server.exe -hf ggml-org/gemma-4-26B-A4B-it-GGUF:Q4_K_M -ngl 99 --r...
Back to top