fix: Fix Triton server model loading error (#584)

awslabs · Jul 15, 2024 · be5e370 · be5e370
1 parent c75a6c5
commit be5e370
Showing 1 changed file with 2 additions and 2 deletions.
diff --git a/ai-ml/nvidia-triton-server/nvidia-triton-server.tf b/ai-ml/nvidia-triton-server/nvidia-triton-server.tf
@@ -53,11 +53,11 @@ module "triton_server_vllm" {
         limits:
           cpu: 10
           memory: 60Gi
-          nvidia.com/gpu: 1
+          nvidia.com/gpu: 4
         requests:
           cpu: 10
           memory: 60Gi
-          nvidia.com/gpu: 1
+          nvidia.com/gpu: 4
       nodeSelector:
         NodeGroupType: g5-gpu-karpenter
         type: karpenter