Unable to Use Multiple Devices on the OpenVINO™ GenAI LLM Benchmark
Content Type: Error Messages | Article ID: 000101740 | Last Reviewed: 03/26/2026
Ran Benchmarking Script for Large Language Models with multiple Intel® Arc™ Pro B60 Graphics. Received error:
Continuous batching: execution device is expected to be CPU or GPU, but got 2 devices
The continuous batching in openvino_genai.LLMPipeline(…) is currently not supporting multi-device execution; it only supports a single execution device, either CPU or GPU.