Add vllm user to avoid get user issue during torch compilation (#111)

* Add vllm user to avoid get user issue during torch compilation

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

* Update xeon-values.yaml

* Update vLLM cpu image

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

---------

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:v0.21.0'
+          image-ref: 'vllm/vllm-openai-cpu:v0.21.0'
           severity: 'HIGH,CRITICAL'
           exit-code: 0
           format: 'table'

core/helm-charts/vllm/values.yaml

@@ -21,7 +21,7 @@ accelDevice: ""
 port: 2080
 shmSize: 1Gi
 image:
-  repository: public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo
+  repository: vllm/vllm-openai-cpu
   # 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.

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

@@ -26,7 +26,7 @@ max_model_len: 8192
 
 # vLLM CPU image configuration
 image:
-  repository: public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo
+  repository: vllm/vllm-openai-cpu
   tag: "v0.21.0"
   pullPolicy: IfNotPresent
 
@@ -58,6 +58,7 @@ modelConfigs:
       VLLM_CPU_NUM_OF_RESERVED_CPU: "0"
       HF_HUB_DISABLE_XET: "1"
       VLLM_CPU_SGL_KERNEL: "1"
+      USER: "vllm"
     extraCmdArgs:
       [
         "--block-size",
@@ -89,6 +90,7 @@ modelConfigs:
       VLLM_CPU_NUM_OF_RESERVED_CPU: "0"
       VLLM_CPU_SGL_KERNEL: "1"
       HF_HUB_DISABLE_XET: "1"
+      USER: "vllm"
     extraCmdArgs:
       [
         "--block-size",
@@ -120,6 +122,7 @@ modelConfigs:
       VLLM_CPU_NUM_OF_RESERVED_CPU: "0"
       VLLM_CPU_SGL_KERNEL: "1"
       HF_HUB_DISABLE_XET: "1"
+      USER: "vllm"
     extraCmdArgs:
       [
         "--block-size",
@@ -149,6 +152,7 @@ modelConfigs:
       VLLM_CPU_NUM_OF_RESERVED_CPU: "0"
       VLLM_CPU_SGL_KERNEL: "1"
       HF_HUB_DISABLE_XET: "1"
+      USER: "vllm"
     extraCmdArgs:
       [
         "--block-size",
@@ -178,6 +182,7 @@ modelConfigs:
       VLLM_CPU_NUM_OF_RESERVED_CPU: "0"
       VLLM_CPU_SGL_KERNEL: "1"
       HF_HUB_DISABLE_XET: "1"
+      USER: "vllm"
     extraCmdArgs:
       [
         "--block-size",
@@ -209,6 +214,7 @@ modelConfigs:
       VLLM_CPU_NUM_OF_RESERVED_CPU: "0"
       VLLM_CPU_SGL_KERNEL: "1"
       HF_HUB_DISABLE_XET: "1"
+      USER: "vllm"
     extraCmdArgs:
       [
         "--block-size",
@@ -242,6 +248,7 @@ modelConfigs:
       VLLM_CPU_SGL_KERNEL: "1"
       HF_HUB_DISABLE_XET: "1"
       LOGNAME: "vllm"
+      USER: "vllm"
     extraCmdArgs:
       [
         "--block-size",
@@ -273,6 +280,7 @@ defaultModelConfigs:
     VLLM_CPU_NUM_OF_RESERVED_CPU: "0"
     VLLM_CPU_SGL_KERNEL: "1"
     HF_HUB_DISABLE_XET: "1"
+    USER: "vllm"
   extraCmdArgs:
     [
       "--block-size",

core/scripts/vllm-quickstart/README.md

@@ -116,7 +116,7 @@ The `models.json` file contains all configuration:
 ```json
 {
   "docker": {
-    "image": "public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.11.2",
+    "image": "vllm/vllm-openai-cpu:v0.21.0",
     "port": "8000:8000",
     "environment": { ... },
     "volumes": [ ... ]

core/scripts/vllm-quickstart/models.json

@@ -1,6 +1,6 @@
 {
   "docker": {
-    "image": "public.ecr.aws/q9t5s3a7/vllm-cpu-release-repo:v0.11.2",
+    "image": "vllm/vllm-openai-cpu:v0.21.0",
     "port": "8000:8000",
     "environment": {
       "VLLM_CPU_SGL_KERNEL": "1",