From b21472d40bc5ad8829670da15e70f53d5fd8e816 Mon Sep 17 00:00:00 2001 From: blaise-muhirwa Date: Tue, 31 Oct 2023 21:19:51 +0000 Subject: [PATCH] update backend triton server image --- .../k3s/inference_deployment/inference_deployment_template.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/deploy/k3s/inference_deployment/inference_deployment_template.yaml b/deploy/k3s/inference_deployment/inference_deployment_template.yaml index 45d3ed7f..c438c487 100644 --- a/deploy/k3s/inference_deployment/inference_deployment_template.yaml +++ b/deploy/k3s/inference_deployment/inference_deployment_template.yaml @@ -40,7 +40,7 @@ spec: maxUnavailable: 0 # Aim for no downtime during rollout containers: - name: inference-server - image: 723181461334.dkr.ecr.us-west-2.amazonaws.com/gl-tritonserver:59d8771ee-tyler-poetry-and-serving-img-updates + image: 723181461334.dkr.ecr.us-west-2.amazonaws.com/gl-tritonserver:929c52e9d-main imagePullPolicy: IfNotPresent # Tritonserver will look for models in /mnt/models and initialize them on startup. # When running multiple instances of Triton server on the same machine that use Python models,