Sync values yaml file for 1.3 release (#1748)

Signed-off-by: Dolpher Du <dolpher.du@intel.com>

DocSum/kubernetes/helm/cpu-tgi-values.yaml

@@ -0,0 +1,9 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+llm-uservice:
+  DOCSUM_BACKEND: "TGI"
+tgi:
+  enabled: true
+vllm:
+  enabled: false

DocSum/kubernetes/helm/cpu-values.yaml

@@ -1,7 +1,9 @@
-# Copyright (C) 2024 Intel Corporation
+# Copyright (C) 2025 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
+llm-uservice:
+  DOCSUM_BACKEND: "vLLM"
 tgi:
-  enabled: true
-vllm:
   enabled: false
+vllm:
+  enabled: true

DocSum/kubernetes/helm/gaudi-tgi-values.yaml

@@ -0,0 +1,32 @@
+# Copyright (C) 2025 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+vllm:
+  enabled: false
+
+llm-uservice:
+  DOCSUM_BACKEND: "TGI"
+
+tgi:
+  enabled: true
+  accelDevice: "gaudi"
+  image:
+    repository: ghcr.io/huggingface/tgi-gaudi
+    tag: "2.3.1"
+  resources:
+    limits:
+      habana.ai/gaudi: 1
+  CUDA_GRAPHS: ""
+  ENABLE_HPU_GRAPH: true
+  LIMIT_HPU_GRAPH: true
+  USE_FLASH_ATTENTION: true
+  FLASH_ATTENTION_RECOMPUTE: true
+  readinessProbe:
+    initialDelaySeconds: 5
+    periodSeconds: 5
+    timeoutSeconds: 1
+  startupProbe:
+    initialDelaySeconds: 5
+    periodSeconds: 5
+    timeoutSeconds: 1
+    failureThreshold: 120

DocSum/kubernetes/helm/gaudi-values.yaml

@@ -1,36 +1,32 @@
-# Copyright (C) 2024 Intel Corporation
+# Copyright (C) 2025 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-vllm:
+# Accelerate inferencing in heaviest components to improve performance
+# by overriding their subchart values
+
+tgi:
   enabled: false
 
 llm-uservice:
-  DOCSUM_BACKEND: "TGI"
+  DOCSUM_BACKEND: "vLLM"
+  retryTimeoutSeconds: 720
 
-tgi:
+vllm:
   enabled: true
-  accelDevice: "gaudi"
   image:
-    repository: ghcr.io/huggingface/tgi-gaudi
-    tag: "2.3.1"
+    repository: opea/vllm-gaudi
   resources:
     limits:
       habana.ai/gaudi: 1
-  CUDA_GRAPHS: ""
-  ENABLE_HPU_GRAPH: true
-  LIMIT_HPU_GRAPH: true
-  USE_FLASH_ATTENTION: true
-  FLASH_ATTENTION_RECOMPUTE: true
-  livenessProbe:
-    initialDelaySeconds: 5
-    periodSeconds: 5
-    timeoutSeconds: 1
-  readinessProbe:
-    initialDelaySeconds: 5
-    periodSeconds: 5
-    timeoutSeconds: 1
   startupProbe:
-    initialDelaySeconds: 5
-    periodSeconds: 5
-    timeoutSeconds: 1
-    failureThreshold: 120
+    failureThreshold: 360
+
+  PT_HPU_ENABLE_LAZY_COLLECTIVES: "true"
+  OMPI_MCA_btl_vader_single_copy_mechanism: "none"
+
+  extraCmdArgs: [
+    "--tensor-parallel-size", "1",
+    "--block-size", "128",
+    "--max-num-seqs", "256",
+    "--max-seq_len-to-capture", "2048"
+  ]