diff --git a/charts/llm-engine/templates/_helpers.tpl b/charts/llm-engine/templates/_helpers.tpl
index 04c8168f..08af45f4 100644
--- a/charts/llm-engine/templates/_helpers.tpl
+++ b/charts/llm-engine/templates/_helpers.tpl
@@ -344,7 +344,7 @@ volumeMounts:
 {{- define "llmEngine.forwarderVolumeMounts" }}
 volumeMounts:
   - name: config-volume
-    mountPath: /root/.aws/config
+    mountPath: /home/user/.aws/config
     subPath: config
   - name: user-config
     mountPath: /workspace/user_config
diff --git a/charts/llm-engine/templates/service_template_config_map.yaml b/charts/llm-engine/templates/service_template_config_map.yaml
index 87b992cf..08ce1424 100644
--- a/charts/llm-engine/templates/service_template_config_map.yaml
+++ b/charts/llm-engine/templates/service_template_config_map.yaml
@@ -180,7 +180,7 @@ data:
                 - ddtrace-run
                 - run-service
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
+                - /workspace/server/llm_engine_server/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
                 - --http
                 - production_threads
                 - --port
@@ -221,9 +221,9 @@ data:
                 - ddtrace-run
                 - python
                 - -m
-                - llm_engine.inference.forwarding.http_forwarder
+                - server.llm_engine_server.inference.forwarding.http_forwarder
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/service--http_forwarder.yaml
+                - /workspace/server/llm_engine_server/inference/configs/service--http_forwarder.yaml
                 - --port
                 - "${FORWARDER_PORT}"
                 - --num-workers
@@ -266,7 +266,7 @@ data:
                 - ddtrace-run
                 - run-service
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
+                - /workspace/server/llm_engine_server/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
                 - --queue
                 - "${QUEUE}"
                 - --task-visibility
diff --git a/charts/llm-engine/values_sample.yaml b/charts/llm-engine/values_sample.yaml
index 7b2cbbf0..06d70362 100644
--- a/charts/llm-engine/values_sample.yaml
+++ b/charts/llm-engine/values_sample.yaml
@@ -1,7 +1,7 @@
 # This is a YAML-formatted file.
 
 # tag [required] is the LLM Engine docker image tag
-tag: 1defd4f9c5376149e27673e154731a0c7820fe5d
+tag: 41ecada1b51ce3a46bbc3190a36ed7890db370d3
 # context is a user-specified deployment tag. Can be used to 
 context: production
 image:
@@ -171,6 +171,20 @@ imageCache:
         - key: "nvidia.com/gpu"
           operator: "Exists"
           effect: "NoSchedule"
+    - name: a100
+      nodeSelector:
+        k8s.amazonaws.com/accelerator: nvidia-ampere-a100
+      tolerations:
+        - key: "nvidia.com/gpu"
+          operator: "Exists"
+          effect: "NoSchedule"
+    - name: t4
+      nodeSelector:
+        k8s.amazonaws.com/accelerator: nvidia-tesla-t4
+      tolerations:
+        - key: "nvidia.com/gpu"
+          operator: "Exists"
+          effect: "NoSchedule"
 
 # celeryBrokerType specifies the celery broker type for async endpoints (coming soon)
 celeryBrokerType: sqs
diff --git a/server/llm_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py b/server/llm_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
index 482a4519..8de7ef72 100644
--- a/server/llm_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
+++ b/server/llm_engine_server/domain/use_cases/llm_model_endpoint_use_cases.py
@@ -227,7 +227,7 @@ async def create_text_generation_inference_bundle(
                     schema_location="TBA",
                     flavor=StreamingEnhancedRunnableImageFlavor(
                         flavor=ModelBundleFlavorType.STREAMING_ENHANCED_RUNNABLE_IMAGE,
-                        repository="text-generation-inference",  # TODO: let user choose repo
+                        repository="ghcr.io/huggingface/text-generation-inference",  # TODO: let user choose repo
                         tag=framework_image_tag,
                         command=command,
                         streaming_command=command,
diff --git a/server/llm_engine_server/infra/gateways/resources/templates/service_template_config_map_circleci.yaml b/server/llm_engine_server/infra/gateways/resources/templates/service_template_config_map_circleci.yaml
index 41ffe75b..3f2e519f 100644
--- a/server/llm_engine_server/infra/gateways/resources/templates/service_template_config_map_circleci.yaml
+++ b/server/llm_engine_server/infra/gateways/resources/templates/service_template_config_map_circleci.yaml
@@ -114,7 +114,7 @@ data:
                 - ddtrace-run
                 - run-service
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
+                - /workspace/server/llm_engine_server/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
                 - --queue
                 - "${QUEUE}"
                 - --task-visibility
@@ -383,7 +383,7 @@ data:
                 - ddtrace-run
                 - run-service
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
+                - /workspace/server/llm_engine_server/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
                 - --queue
                 - "${QUEUE}"
                 - --task-visibility
@@ -805,7 +805,7 @@ data:
                 - ddtrace-run
                 - run-service
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
+                - /workspace/server/llm_engine_server/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
                 - --http
                 - production_threads
                 - --port
@@ -1071,7 +1071,7 @@ data:
                 - ddtrace-run
                 - run-service
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
+                - /workspace/server/llm_engine_server/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
                 - --http
                 - production_threads
                 - --port
@@ -1473,9 +1473,9 @@ data:
                 - ddtrace-run
                 - python
                 - -m
-                - llm_engine.inference.forwarding.http_forwarder
+                - server.llm_engine_server.inference.forwarding.http_forwarder
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/service--http_forwarder.yaml
+                - /workspace/server/llm_engine_server/inference/configs/service--http_forwarder.yaml
                 - --port
                 - "${FORWARDER_PORT}"
                 - --num-workers
@@ -1712,7 +1712,7 @@ data:
                 - ddtrace-run
                 - run-service
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
+                - /workspace/server/llm_engine_server/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
                 - --queue
                 - "${QUEUE}"
                 - --task-visibility
@@ -1987,7 +1987,7 @@ data:
                 - ddtrace-run
                 - run-service
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
+                - /workspace/server/llm_engine_server/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
                 - --queue
                 - "${QUEUE}"
                 - --task-visibility
@@ -2421,7 +2421,7 @@ data:
                 - ddtrace-run
                 - run-service
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
+                - /workspace/server/llm_engine_server/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
                 - --http
                 - production_threads
                 - --port
@@ -2693,7 +2693,7 @@ data:
                 - ddtrace-run
                 - run-service
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
+                - /workspace/server/llm_engine_server/inference/configs/${FORWARDER_CONFIG_FILE_NAME}
                 - --http
                 - production_threads
                 - --port
@@ -3107,9 +3107,9 @@ data:
                 - ddtrace-run
                 - python
                 - -m
-                - llm_engine.inference.forwarding.http_forwarder
+                - server.llm_engine_server.inference.forwarding.http_forwarder
                 - --config
-                - /workspace/llm_engine/llm_engine/inference/configs/service--http_forwarder.yaml
+                - /workspace/server/llm_engine_server/inference/configs/service--http_forwarder.yaml
                 - --port
                 - "${FORWARDER_PORT}"
                 - --num-workers