update trtllm resources (#1156)

GoogleCloudPlatform · Feb 23, 2024 · 07fef45 · 07fef45
1 parent f743171
commit 07fef45
Showing 1 changed file with 4 additions and 4 deletions.
diff --git a/ai-ml/llm-serving-gemma/trtllm/deploy-triton-server.yaml b/ai-ml/llm-serving-gemma/trtllm/deploy-triton-server.yaml
@@ -59,12 +59,12 @@ spec:
         imagePullPolicy: IfNotPresent
         resources:
           requests:
-            ephemeral-storage: "100G"
-            memory: "100G"
+            ephemeral-storage: "40Gi"
+            memory: "40Gi"
             nvidia.com/gpu: 1
           limits:
-            ephemeral-storage: "100G"
-            memory: "100G"
+            ephemeral-storage: "40Gi"
+            memory: "40Gi"
             nvidia.com/gpu: 1
         command:
         - /scripts/entrypoint.sh