Model serving endpoint creation failed
Options
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
01-30-2025 01:04 AM - edited 01-30-2025 01:11 AM
I have a logged pyfunc mlflow model that runs without issues in a databricks notebook using
"mlflow.pyfunc.load_model()". I can deploy it without issues as a model serving endpoint with "workload_type" set to GPU, but when i try to update the endpoint to CPU it fails with this repeating error:
"[pb897] [2025-01-29 14:50:40 +0000] [4014] [INFO] Booting worker with pid: 4014 [pb897] [2025-01-29 14:50:42 +0000] [9] [ERROR] Worker (pid:3932) was sent code 132!"
"[pb897] [2025-01-29 14:50:40 +0000] [4014] [INFO] Booting worker with pid: 4014 [pb897] [2025-01-29 14:50:42 +0000] [9] [ERROR] Worker (pid:3932) was sent code 132!"
Why can the exact same configuration run on an environment with GPU but not on a CPU only environment?
I have also tried deleting the endpoint and try re-create it with the CPU config.
