vLLM cpu image upgrade to v0.21.0 (#110)

Signed-off-by: sandeshk <sandesh.kumar.s@intel.com>

Author: sandeshk-intel

.github/workflows/code-scans.yaml

@@ -52,7 +52,7 @@ jobs:
         continue-on-error: true
         with:
           scan-type: 'image'
-          image-ref: 'public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.10.2'
+          image-ref: 'public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.21.0'
           severity: 'HIGH,CRITICAL'
           exit-code: 0
           format: 'table'

core/helm-charts/vllm/values.yaml

@@ -25,7 +25,7 @@ image:
   # Uncomment the following line to set desired image pull policy if needed, as one of Always, IfNotPresent, Never.
   # pullPolicy: ""
   # Overrides the image tag whose default is the chart appVersion.
-  tag: "v0.10.2"
+  tag: "v0.21.0"
 
 imagePullSecrets: []
 nameOverride: ""

core/helm-charts/vllm/xeon-values.yaml

@@ -27,7 +27,7 @@ max_model_len: 8192
 # vLLM CPU image configuration
 image:
   repository: public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo
-  tag: "v0.10.2"
+  tag: "v0.21.0"
   pullPolicy: IfNotPresent
 
 # Node affinity for Xeon inference nodes
@@ -74,7 +74,6 @@ modelConfigs:
         "2048",
         "--max-num-seqs",
         "256",
-        "--disable-log-requests",
         "--enable-auto-tool-choice",
         "--tool-call-parser", "llama3_json",
       ]
@@ -137,7 +136,6 @@ modelConfigs:
         "2048",
         "--max-num-seqs",
         "256",
-        "--disable-log-requests",        
       ]
     tensor_parallel_size: "{{ .Values.tensor_parallel_size }}"
     pipeline_parallel_size: "{{ .Values.pipeline_parallel_size }}"
@@ -167,7 +165,6 @@ modelConfigs:
         "2048",
         "--max-num-seqs",
         "256",
-        "--disable-log-requests",       
       ]
     tensor_parallel_size: "{{ .Values.tensor_parallel_size }}"
     pipeline_parallel_size: "{{ .Values.pipeline_parallel_size }}"