Local AI Glossary
What is ROCm (Radeon Open Compute)?
Source: local-llm.net/glossary
AMD's open-source platform for GPU computing, analogous to NVIDIA's CUDA. ROCm enables AI inference on AMD GPUs. Support has improved significantly in llama.cpp and vLLM, though the ecosystem is less mature than CUDA. Best supported on Linux.
How ROCm (Radeon Open Compute) fits in the local AI stack
ROCm (Radeon Open Compute) is part of the broader local AI ecosystem. See the related guides, comparisons, and tools below to see how it applies in practice.
See also
- Full Local AI Glossary
- All learn topics
- What is Local AI?
- Quantization explained
- Hardware requirements
- How to choose a local LLM