Files
ubicloud/rhizome/inference_endpoint/bin/setup-replica
Benjamin Satzger 09cec4e2bc Set max_concurrency of inference gateway
In a previous commit we added max_concurrency to inference endpoints. In
this commit we set inference gateway's corresponding setting
IG_MAX_REQUESTS to that value during replica setup.
2025-02-11 17:47:12 +01:00

879 B
Executable File