fix: bump up the version of container images (#365)

* bump the image version of webapp (#364)

Signed-off-by: yimingl (generated by with_the_same_user script) <yimingl@viking-prod-234.ipp2a1.colossus.nvidia.com>
Co-authored-by: yimingl (generated by with_the_same_user script) <yimingl@viking-prod-234.ipp2a1.colossus.nvidia.com>
Signed-off-by: yimingl (generated by with_the_same_user script) <yimingl@viking-prod-234.ipp2a1.colossus.nvidia.com>

* bump up the image version used by generator

Signed-off-by: yimingl (generated by with_the_same_user script) <yimingl@viking-prod-234.ipp2a1.colossus.nvidia.com>

---------

Signed-off-by: yimingl (generated by with_the_same_user script) <yimingl@viking-prod-234.ipp2a1.colossus.nvidia.com>
Co-authored-by: yimingl (generated by with_the_same_user script) <yimingl@viking-prod-234.ipp2a1.colossus.nvidia.com>

Author: Arsene12358

src/aiconfigurator/generator/config/deployment_config.yaml

@@ -59,11 +59,11 @@ inputs:
     default: "dynamo"
   - key: K8sConfig.k8s_image
     required: false
-    default: &default_trtllm_image "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.8.0"
+    default: &default_trtllm_image "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.9.0"
     backend_defaults:
       trtllm: *default_trtllm_image
-      vllm: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.8.0"
-      sglang: "nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.8.0"
+      vllm: "nvcr.io/nvidia/ai-dynamo/vllm-runtime:0.9.0"
+      sglang: "nvcr.io/nvidia/ai-dynamo/sglang-runtime:0.9.0"
   - key: K8sConfig.k8s_image_pull_secret
     required: false
     default: ""

src/aiconfigurator/webapp/components/profiling/sdk/config.py

@@ -15,7 +15,10 @@
 
 import yaml
 
-from aiconfigurator.generator.api import generate_backend_artifacts, generate_config_from_input_dict
+from aiconfigurator.generator.api import (
+    generate_backend_artifacts,
+    generate_config_from_input_dict,
+)
 
 # Constants
 DECODE_MAX_CONCURRENCY = 1024
@@ -72,7 +75,7 @@ def generate_config_yaml(
         "K8sConfig": {
             "name_prefix": name_prefix,
             "k8s_namespace": "dynamo",
-            "k8s_image": "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.8.0",
+            "k8s_image": "nvcr.io/nvidia/ai-dynamo/tensorrtllm-runtime:0.9.0",
             "k8s_model_cache": "model-cache",
             "k8s_engine_mode": "inline",
         },