https://community.databricks.com/t5/generative-ai/how-can-i-utilize-multiple-gpus-from-multiple-nodes-in/m-p/147351#M1616 <P>Can you try the Serverless GPU Compute?&nbsp;<A href="https://docs.databricks.com/aws/en/machine-learning/sgc-examples/gpu-batch-inference" target="_blank">https://docs.databricks.com/aws/en/machine-learning/sgc-examples/gpu-batch-inference</A></P> Sat, 07 Feb 2026 01:42:36 GMT lin-yuan 2026-02-07T01:42:36Z https://community.databricks.com/t5/generative-ai/how-can-i-utilize-multiple-gpus-from-multiple-nodes-in/m-p/61073#M32 <P><SPAN>I am currently experimenting with the whisper model for batchwise inference on Databricks and have successfully utilized multiple instances of the model by accessing multiple GPUs available in the driver node. However, I am wondering how I can leverage the multiple GPUs present in each of the worker nodes, as I am unable to access them. I have come across documentation on utilizing all worker nodes with pyspark-based libraries, but I am specifically interested in how to achieve this with a transformer model like whisper. Any insights or suggestions would be greatly appreciated.</SPAN></P> Mon, 19 Feb 2024 11:38:38 GMT https://community.databricks.com/t5/generative-ai/how-can-i-utilize-multiple-gpus-from-multiple-nodes-in/m-p/61073#M32 Mathew 2024-02-19T11:38:38Z https://community.databricks.com/t5/generative-ai/how-can-i-utilize-multiple-gpus-from-multiple-nodes-in/m-p/147351#M1616 <P>Can you try the Serverless GPU Compute?&nbsp;<A href="https://docs.databricks.com/aws/en/machine-learning/sgc-examples/gpu-batch-inference" target="_blank">https://docs.databricks.com/aws/en/machine-learning/sgc-examples/gpu-batch-inference</A></P> Sat, 07 Feb 2026 01:42:36 GMT https://community.databricks.com/t5/generative-ai/how-can-i-utilize-multiple-gpus-from-multiple-nodes-in/m-p/147351#M1616 lin-yuan 2026-02-07T01:42:36Z