updated

Signed-off-by: Harika <codewith3@gmail.com>

Author: xkd9

core/playbooks/deploy-keycloak-tls-cert.yml

@@ -1,8 +1,4 @@
-<<<<<<< HEAD
 # Copyright (C) 2025-2026 Intel Corporation
-=======
-# Copyright (C) 2024-2025 Intel Corporation
->>>>>>> dell-deploy-1.4-nv
 # SPDX-License-Identifier: Apache-2.0
 ---
 - name: Create Keycloak TLS secret
@@ -59,18 +55,6 @@
     - name: Display the output
       debug:
         msg: "Secret {{ secret_name }} created."
-<<<<<<< HEAD
-    - name: Retrieve number of Infrastructure Nodes (ei-infra-eligible)
-      ansible.builtin.shell: kubectl get nodes --selector=ei-infra-eligible=true --no-headers | wc -l
-      register: inference_node_count
-      changed_when: false
-    - name: Set Keycloak Replicas based upon Infrastructure Nodes
-      set_fact:
-        inference_infra_replica_count: "{{ inference_node_count.stdout | int if inference_node_count.stdout | int > 0 else 1 }}"
-    - name: Display the number of Infrastructure Nodes
-      debug:
-        msg: "Number of ei-infra-eligible nodes configured: {{ inference_infra_replica_count }}"
-=======
     - name: Retrieve number of Inference Infrastructure Nodes
       ansible.builtin.shell: kubectl get nodes --selector=role=inference-infra --no-headers | wc -l
       register: inference_node_count
@@ -81,7 +65,6 @@
     - name: Display the number of Inference Infrastructure Nodes
       debug:
         msg: "Number of inference-infra node configured: {{ inference_infra_replica_count }}"
->>>>>>> dell-deploy-1.4-nv
       run_once: true
       when: deploy_keycloak == "yes"
     - name: Delete genai-gateway-ingress resource
@@ -119,41 +102,10 @@
               persistence:
                 enabled: true
                 size: 8Gi
-<<<<<<< HEAD
-              tolerations:
-                - key: node-role.kubernetes.io/control-plane
-                  operator: Exists
-                  effect: NoSchedule
-                - key: node-role.kubernetes.io/master
-                  operator: Exists
-                  effect: NoSchedule
-              affinity:
-                nodeAffinity:
-                  requiredDuringSchedulingIgnoredDuringExecution:
-                    nodeSelectorTerms:
-                    - matchExpressions:
-                      - key: ei-infra-eligible
-                        operator: In
-                        values: ["true"]
-=======
->>>>>>> dell-deploy-1.4-nv
             volumePermissions:
               enabled: true
               image:
                 repository: bitnamilegacy/os-shell
-<<<<<<< HEAD
-                tag: 12-debian-12-r48
-          production: true
-          proxy: edge
-          replicaCount: "{{ inference_infra_replica_count | int }}"
-          resources:
-            requests:
-              memory: "2Gi"
-              cpu: "500m"
-            limits:
-              memory: "4Gi"
-              cpu: "1500m"
-=======
                 tag: 12-debian-12-r48 
             tolerations:
               - key: node-role.kubernetes.io/control-plane
@@ -176,7 +128,6 @@
           production: true
           proxy: edge
           replicaCount: "{{ inference_infra_replica_count | int }}"
->>>>>>> dell-deploy-1.4-nv
           extraEnvVars:
             - name: KC_CACHE
               value: ispn
@@ -232,15 +183,9 @@
               requiredDuringSchedulingIgnoredDuringExecution:
                 nodeSelectorTerms:
                 - matchExpressions:
-<<<<<<< HEAD
-                  - key: ei-infra-eligible
-                    operator: In
-                    values: ["true"]
-=======
                   - key: role
                     operator: In
                     values: ["infra"]
->>>>>>> dell-deploy-1.4-nv
                 - matchExpressions:
                   - key: node-role.kubernetes.io/control-plane
                     operator: Exists
@@ -346,18 +291,10 @@
             annotations:
               alb.ingress.kubernetes.io/actions.ssl-redirect: '{"Type": "redirect", "RedirectConfig": { "Protocol": "HTTPS", "Port": "443", "StatusCode": "HTTP_301"}}'
               alb.ingress.kubernetes.io/certificate-arn: "{{ aws_certificate_arn | default('') }}"
-<<<<<<< HEAD
-              alb.ingress.kubernetes.io/group.name: ei-eks
-              alb.ingress.kubernetes.io/listen-ports: '[{"HTTP": 80}, {"HTTPS": 443}]'
-              alb.ingress.kubernetes.io/scheme: internet-facing
-              alb.ingress.kubernetes.io/target-type: ip
-              alb.ingress.kubernetes.io/group.order: '3'
-=======
               alb.ingress.kubernetes.io/group.name: keycloak-apisix
               alb.ingress.kubernetes.io/listen-ports: '[{"HTTP": 80}, {"HTTPS": 443}]'
               alb.ingress.kubernetes.io/scheme: internet-facing
               alb.ingress.kubernetes.io/target-type: ip
->>>>>>> dell-deploy-1.4-nv
           spec:
             ingressClassName: alb
             rules:

core/roles/utils/tasks/get_optimized_cpu_topology.yaml

@@ -1,8 +1,4 @@
-<<<<<<< HEAD
 # Copyright (C) 2025-2026 Intel Corporation
-=======
-# Copyright (C) 2024-2025 Intel Corporation
->>>>>>> dell-deploy-1.4-nv
 # SPDX-License-Identifier: Apache-2.0
 
 ---
@@ -32,11 +28,6 @@
                 requiredDuringSchedulingIgnoredDuringExecution:
                   nodeSelectorTerms:
                   - matchExpressions:
-<<<<<<< HEAD
-                    - key: ei-inference-eligible
-                      operator: In
-                      values: ["true"]
-=======
                     - key: role
                       operator: In
                       values: ["inference"]
@@ -48,7 +39,6 @@
                     - key: role
                       operator: In
                       values: ["inference-cpu"]
->>>>>>> dell-deploy-1.4-nv
             tolerations:
               - operator: Exists # Allow scheduling on any node including master
             securityContext:
@@ -235,20 +225,6 @@
   tags:
     - install
 
-<<<<<<< HEAD
-- name: Refresh node-topology-optimizer pod name (avoid stale pod references)
-  ansible.builtin.command: >
-    kubectl -n kube-system get pods -l app=node-topology-optimizer
-    -o jsonpath='{.items[0].metadata.name}'
-  register: optimizer_pod_name_refresh
-  changed_when: false
-
-- name: Set refreshed optimizer_pod_name
-  ansible.builtin.set_fact:
-    optimizer_pod_name: "{{ optimizer_pod_name_refresh.stdout | trim }}"
-
-=======
->>>>>>> dell-deploy-1.4-nv
 - name: Get detailed CPU information
   kubernetes.core.k8s_exec:
     pod: "{{ optimizer_pod_name }}"
@@ -301,11 +277,7 @@
       for s in $(seq 0 $((total_sockets - 1))); do
         socket_totals[$s]=0;
       done;
-<<<<<<< HEAD
-
-=======
       
->>>>>>> dell-deploy-1.4-nv
       for i in $(seq 0 $((total_numa - 1))); do
         numa_cpus=$(lscpu | grep "NUMA node$i CPU(s):" | cut -d: -f2 | xargs);
         if [[ "$numa_cpus" != "" ]]; then
@@ -340,46 +312,6 @@
   tags:
     - install
 
-<<<<<<< HEAD
-- name: Read CPU reservation script content
-  ansible.builtin.set_fact:
-    cpu_script_content: "{{ lookup('file', role_path + '/files/compute_reserved_cpus.sh') }}"
-  tags:
-    - install
-
-- name: Execute CPU reservation computation directly from script file
-  ansible.builtin.shell:
-    cmd: echo {{ cpu_script_content | quote }} | kubectl exec -n kube-system {{ optimizer_pod_name | quote }} -c ubuntu -i -- bash -s {{ nri_total_reserved_cpus | default(8) | int }}
-  register: computed_reserved_cpu_list
-  changed_when: false
-  tags:
-    - install
-
-- name: Set nri_reserved_cpu_list fact
-  ansible.builtin.set_fact:
-    nri_reserved_cpu_list: >-
-      {{
-        (computed_reserved_cpu_list.stdout | default('') | trim)
-        | regex_replace('^.*NRI_RESERVED_CPU_LIST=', '')
-        | regex_replace('\\s.*$', '')
-        | regex_replace(',+$', '')
-      }}
-
-- name: Assert nri_reserved_cpu_list computed
-  ansible.builtin.assert:
-    that:
-      - nri_reserved_cpu_list | length > 0
-    fail_msg: >-
-      Failed to compute nri_reserved_cpu_list.
-      stdout={{ computed_reserved_cpu_list.stdout | default('') }}
-      stderr={{ computed_reserved_cpu_list.stderr | default('') }}
-
-- name: Debug final nri_reserved_cpu_list
-  ansible.builtin.debug:
-    msg: "nri_reserved_cpu_list={{ nri_reserved_cpu_list }}"
-
-=======
->>>>>>> dell-deploy-1.4-nv
 - name: Parse accurate CPU topology results
   ansible.builtin.set_fact:
     numa_cpu_counts: >-
@@ -594,25 +526,6 @@
   tags:
     - install
 
-<<<<<<< HEAD
-- name: Calculate workload CPUs
-  ansible.builtin.set_fact:
-    workload_cpus: >-
-      {%- set total_cpus = (cpus_per_socket | int) * (total_sockets.stdout | int) -%}
-      {%- set reserved_cpu_count = nri_reserved_cpu_list.split(',') | length -%}
-      {%- if reserved_cpu_count >= total_cpus -%}{%- set reserved_cpu_count = total_cpus -%}{%- endif -%}
-      {{ total_cpus - reserved_cpu_count }}
-  tags:
-    - install
-
-- name: Add workload_cpus to balloon configuration
-  ansible.builtin.set_fact:
-    optimal_balloon_config: "{{ optimal_balloon_config | combine({'workload_cpus': workload_cpus | int}) }}"
-  tags:
-    - install
-
-=======
->>>>>>> dell-deploy-1.4-nv
 - name: Check for AMX support
   kubernetes.core.k8s_exec:
     pod: "{{ optimizer_pod_name }}"
@@ -660,13 +573,8 @@
       {% endfor %}
 
       === CPU Features ===
-<<<<<<< HEAD
-      AMX: {{ 'SUPPORTED' if (amx_check is defined and amx_check.rc is defined and amx_check.rc == 0) else 'NOT AVAILABLE' }}
-      AVX-512: {{ 'SUPPORTED' if (avx512_check is defined and avx512_check.rc is defined and avx512_check.rc == 0) else 'NOT AVAILABLE' }}
-=======
       AMX: {{ 'SUPPORTED' if amx_check.rc == 0 else 'NOT AVAILABLE' }}
       AVX-512: {{ 'SUPPORTED' if avx512_check.rc == 0 else 'NOT AVAILABLE' }}
->>>>>>> dell-deploy-1.4-nv
 
       === Parallelism Strategy ===
       Strategy: {{ optimal_balloon_config.strategy }}

core/scripts/generate-vault-secrets.sh

@@ -33,11 +33,6 @@ MINIO_SECRET=$(generate_password 20)
 POSTGRES_USER="postgres"
 POSTGRES_PASSWORD=$(generate_password 20)
 GRAFANA_ADMIN_PASSWORD=$(generate_password 20)
-<<<<<<< HEAD
-AGENTICAI_POSTGRES_PASSWORD=$(generate_password 20)
-AGENTICAI_REDIS_PASSWORD=$(generate_password 20)
-=======
->>>>>>> dell-deploy-1.4-nv
 
 # Generate connection strings
 DATABASE_URL="postgresql://admin:${POSTGRESQL_PASSWORD}@genai-gateway-postgresql:5432/litellm"
@@ -72,11 +67,6 @@ minio_user: "$MINIO_USER"
 postgres_user: "$POSTGRES_USER"
 postgres_password: "$POSTGRES_PASSWORD"
 grafana_admin_password: "$GRAFANA_ADMIN_PASSWORD"
-<<<<<<< HEAD
-agenticai_postgres_password: "$AGENTICAI_POSTGRES_PASSWORD"
-agenticai_redis_password: "$AGENTICAI_REDIS_PASSWORD"
-=======
->>>>>>> dell-deploy-1.4-nv
 EOF
 
 # Set appropriate permissions

docs/README.md

@@ -12,10 +12,6 @@ Complete all [prerequisites](./prerequisites.md).
 
 | Deployment Type                         | Description                                                  |
 |-----------------------------------------|--------------------------------------------------------------|
-<<<<<<< HEAD
-| **Single Node (vLLM, non‑production)**  | For Quick Testing on Intel® Xeon® processors using vLLM Docker ([Guide](../core/scripts/vllm-quickstart/README.md))               |
-=======
->>>>>>> dell-deploy-1.4-nv
 | **Single Node**                         | Quick start for testing or lightweight workloads ([Guide](./single-node-deployment.md)) |
 | **Single Master, Multiple Workers**     | For higher throughput workloads ([Guide](./inventory-design-guide.md#single-master-multiple-workload-node-deployment)) |
 | **Multi-Master, Multiple Workers**      | Recommended for HA enterprise clusters ([Guide](./inventory-design-guide.md#multi-master-multi-workload-node-deployment)) |

docs/cpu-optimization-guide.md

@@ -7,21 +7,6 @@ The system automatically optimizes CPU allocation for AI models using balloon po
 ## Automatic Features
 
 ### CPU Allocation
-<<<<<<< HEAD
-
-**System CPU Reservation**: A total of **8 vCPUs** is reserved for infrastructure components (Keycloak, APISIX, observability, kube-system), distributed evenly across NUMA nodes.
-
-**Intelligent CPU Selection**:
-- Automatically detects NUMA topology and hyperthreading configuration
-- For hyperthreaded systems: Balances reservations between physical cores and HT siblings
-  - Example (48 cores with HT): Reserves from both physical cores (0-23) and HT cores (24-47)
-- For non-segmented CPUs (e.g., "0-47"): Creates virtual segments at the midpoint
-- For segmented CPUs (e.g., "0-23,48-71"): Uses existing segment boundaries
-
-**Model CPU Allocation**:
-- Remaining CPUs (after reservation) are allocated to LLM models
-- Assigns dedicated CPU cores to each model for optimal performance
-=======
 - System automatically detects available CPU cores
 - Reserves 18% of CPUs for system processes
 - Allocates remaining CPUs to AI models
@@ -31,7 +16,6 @@ The system automatically optimizes CPU allocation for AI models using balloon po
 - System automatically detects available memory
 - Reserves 18% of memory for system processes
 - Allocates remaining memory to AI models
->>>>>>> dell-deploy-1.4-nv
 
 ### Hardware Detection
 - Automatically detects NUMA topology
@@ -53,18 +37,6 @@ labels:
 resources:
   requests:
     cpu: 40        # Automatically calculated
-<<<<<<< HEAD
-    # for tp1, tp2 system should have minimum 128Gi and for tp>=4 minimum 256Gi memory available for the model's pod
-    memory: 128Gi  
-```
- 
-## System Component Deployment Recommendations
-
-For single-node Xeon clusters, **Keycloak** and **APISIX** are recommended.
-
-For Gaudi or large multi-node Xeon clusters, the GenAI Gateway is well-suited.
-
-=======
     memory: 4G
 ```
  
@@ -76,7 +48,6 @@ For single node clusters (e.g., systems with 48 CPU cores), only Keycloak and AP
 - For clusters with limited CPU resources, deploy only Keycloak and APISIX.
 - GenAI Gateway deployment requires at least 96 CPU cores.
  
->>>>>>> dell-deploy-1.4-nv
 ## Status Verification
  
 ### Check System Status

docs/examples/multi-node/inference-config.cfg

@@ -17,11 +17,4 @@ deploy_observability=off
 deploy_llm_models=on
 deploy_ceph=off
 deploy_istio=off
-<<<<<<< HEAD
 uninstall_ceph=off
-
-# Agentic AI Plugin
-deploy_agenticai_plugin=off
-=======
-uninstall_ceph=off
->>>>>>> dell-deploy-1.4-nv

docs/examples/single-node/inference-config.cfg

@@ -15,9 +15,3 @@ deploy_llm_models=on
 deploy_ceph=off
 deploy_istio=off
 uninstall_ceph=off
-<<<<<<< HEAD
-
-# Agentic AI Plugin
-deploy_agenticai_plugin=off
-=======
->>>>>>> dell-deploy-1.4-nv

docs/prerequisites.md

@@ -15,11 +15,7 @@ The first step is to get access to the hardware platforms. This guide assumes th
 
 | Category            | Details                                                                                                           |
 |---------------------|-------------------------------------------------------------------------------------------------------------------|
-<<<<<<< HEAD
-| Operating System    | Ubuntu 22.04, Ubuntu 24.04                                                                                                |
-=======
 | Operating System    | Ubuntu 22.04                                                                                                |
->>>>>>> dell-deploy-1.4-nv
 | Hardware Platforms  | 4th Gen Intel® Xeon® Scalable processors<br>5th Gen Intel® Xeon® Scalable processors<br>6th Gen Intel® Xeon® Scalable processors<br>3rd Gen Intel® Xeon® Scalable processors and Intel® Gaudi® 2 AI Accelerator<br>4th Gen Intel® Xeon® Scalable processors and Intel® Gaudi® 2 AI Accelerator <br>6th Gen Intel® Xeon® Scalable processors and Intel® Gaudi® 3 AI Accelerator|
 | Gaudi Firmware Version | 1.20.0 or newer