multi-gpu-llm-toolkit
daimonionnn
Run llama.cpp across two GPUs of different vendors at once (AMD ROCm/HIP or Vulkan + NVIDIA CUDA) in one llama-server process, no RPC server. Windows (PowerShell) and Linux (bash) implementations, shared docs on ROCm memory bugs and benchmarks.
Growth over time
2 data points · 2026-09-06 → 2026-10-03How do you feel about this project?
Ask AI about multi-gpu-llm-toolkit
Question copied to clipboardWhat is the daimonionnn/multi-gpu-llm-toolkit GitHub project? Description: "Run llama.cpp across two GPUs of different vendors at once (AMD ROCm/HIP or Vulkan + NVIDIA CUDA) in one llama-server process, no RPC server. Windows (PowerShell) and Linux (bash) implementations, shared docs on ROCm memory bugs and benchmarks.". Written in Shell. 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 multi-gpu-llm-toolkit
Clone via HTTPS
Clone via SSH
Download ZIP
Download main.zipFound an issue?
Report bugs or request features on the multi-gpu-llm-toolkit issue tracker:
Open GitHub Issues