Skip to content

Commit 648f3dc

Browse files
xkd9Harika
xkd9
authored and
Harika
committed
updated
Signed-off-by: Harika <codewith3@gmail.com>
1 parent 3e967e3 commit 648f3dc

9 files changed

Lines changed: 0 additions & 162 deletions

File tree

‎core/lib/cluster/nodes/add-node.sh‎

Lines changed: 0 additions & 8 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,5 @@
11

2-
<<<<<<< HEAD
32
# Copyright (C) 2025-2026 Intel Corporation
4-
=======
5-
# Copyright (C) 2024-2025 Intel Corporation
6-
>>>>>>> dell-deploy-1.4-nv
73
# SPDX-License-Identifier: Apache-2.0
84

95
add_inference_nodes_playbook() {
@@ -20,11 +16,7 @@ add_inference_nodes_playbook() {
2016

2117
invoke_prereq_workflows "$@"
2218

23-
<<<<<<< HEAD
24-
ansible-playbook -i "${INVENTORY_PATH}" playbooks/cluster.yml --become --become-user=root
25-
=======
2619
ansible-playbook -i "${INVENTORY_PATH}" playbooks/cluster.yml --become --become-user=root --become-password-file="${BECOME_PASSWORD_FILE}"
27-
>>>>>>> dell-deploy-1.4-nv
2820

2921
}
3022

‎core/lib/cluster/state/cluster-state-check.sh‎

Lines changed: 0 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -1,17 +1,9 @@
1-
<<<<<<< HEAD
21
# Copyright (C) 2025-2026 Intel Corporation
3-
=======
4-
# Copyright (C) 2024-2025 Intel Corporation
5-
>>>>>>> dell-deploy-1.4-nv
62
# SPDX-License-Identifier: Apache-2.0
73

84
check_cluster_state() {
95
echo "Checking the state of the Kubernetes cluster..."
10-
<<<<<<< HEAD
11-
ansible-playbook -i inventory/mycluster/hosts.yaml --become --become-user=root upgrade-cluster.yml --check
12-
=======
136
ansible-playbook -i inventory/mycluster/hosts.yaml --become --become-user=root --become-password-file="${BECOME_PASSWORD_FILE}" upgrade-cluster.yml --check
14-
>>>>>>> dell-deploy-1.4-nv
157
# Check the exit status of the Ansible playbook command
168
if [ $? -eq 0 ]; then
179
echo "Kubernetes cluster state check completed successfully."
@@ -23,10 +15,6 @@ check_cluster_state() {
2315

2416
run_k8s_cluster_wait() {
2517
echo "Waiting for Kubernetes control plane to become ready..."
26-
<<<<<<< HEAD
27-
ansible -i "${INVENTORY_PATH}" kube_control_plane -m wait_for -a "port=6443 timeout=600" --become --become-user=root
28-
=======
2918
ansible -i "${INVENTORY_PATH}" kube_control_plane -m wait_for -a "port=6443 timeout=600" --become --become-user=root --become-password-file="${BECOME_PASSWORD_FILE}"
30-
>>>>>>> dell-deploy-1.4-nv
3119
return $?
3220
}

‎core/lib/components/intel-base-operator.sh‎

Lines changed: 0 additions & 12 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,4 @@
1-
<<<<<<< HEAD
21
# Copyright (C) 2025-2026 Intel Corporation
3-
=======
4-
# Copyright (C) 2024-2025 Intel Corporation
5-
>>>>>>> dell-deploy-1.4-nv
62
# SPDX-License-Identifier: Apache-2.0
73

84
run_deploy_habana_ai_operator_playbook() {
@@ -15,19 +11,11 @@ run_deploy_habana_ai_operator_playbook() {
1511
else
1612
gaudi_operator=""
1713
fi
18-
<<<<<<< HEAD
19-
ansible-playbook -i "${INVENTORY_PATH}" --become --become-user=root playbooks/deploy-habana-ai-operator.yml --extra-vars "gaudi_operator=${gaudi_operator}"
20-
=======
2114
ansible-playbook -i "${INVENTORY_PATH}" --become --become-user=root --become-password-file="${BECOME_PASSWORD_FILE}" playbooks/deploy-habana-ai-operator.yml --extra-vars "gaudi_operator=${gaudi_operator}"
22-
>>>>>>> dell-deploy-1.4-nv
2315
if [ $? -eq 0 ]; then
2416
echo "The deploy-habana-ai-operator.yml playbook ran successfully."
2517
else
2618
echo "The deploy-habana-ai-operator.yml playbook encountered an error."
2719
exit 1
2820
fi
29-
<<<<<<< HEAD
3021
}
31-
=======
32-
}
33-
>>>>>>> dell-deploy-1.4-nv

‎core/lib/components/observability-controller.sh‎

Lines changed: 0 additions & 9 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,4 @@
1-
<<<<<<< HEAD
21
# Copyright (C) 2025-2026 Intel Corporation
3-
=======
4-
# Copyright (C) 2024-2025 Intel Corporation
5-
>>>>>>> dell-deploy-1.4-nv
62
# SPDX-License-Identifier: Apache-2.0
73

84
deploy_observability_playbook() {
@@ -22,10 +18,5 @@ deploy_observability_playbook() {
2218

2319
local extra_vars="secret_name=${cluster_url} cert_file=${cert_file} key_file=${key_file} deploy_observability=${deploy_observability} deploy_logging=${deploy_logging} observability_stack_chart_version=${observability_stack_chart_version} kubernetes_platform=${kubernetes_platform}"
2420

25-
<<<<<<< HEAD
26-
ansible-playbook -i "${INVENTORY_PATH}" "$playbook_path" --become --become-user=root --extra-vars "$extra_vars" --tags "$tags" --vault-password-file "$vault_pass_file"
27-
}
28-
=======
2921
ansible-playbook -i "${INVENTORY_PATH}" "$playbook_path" --become --become-user=root --become-password-file="${BECOME_PASSWORD_FILE}" --extra-vars "$extra_vars" --tags "$tags" --vault-password-file "$vault_pass_file"
3022
}
31-
>>>>>>> dell-deploy-1.4-nv

‎core/lib/models/install-model-hf.sh‎

Lines changed: 0 additions & 4 deletions
Original file line numberDiff line numberDiff line change
@@ -1,9 +1,5 @@
11

2-
<<<<<<< HEAD
32
# Copyright (C) 2025-2026 Intel Corporation
4-
=======
5-
# Copyright (C) 2024-2025 Intel Corporation
6-
>>>>>>> dell-deploy-1.4-nv
73
# SPDX-License-Identifier: Apache-2.0
84

95
deploy_from_huggingface() {

‎core/lib/models/install-model.sh‎

Lines changed: 0 additions & 45 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,4 @@
1-
<<<<<<< HEAD
21
# Copyright (C) 2025-2026 Intel Corporation
3-
=======
4-
# Copyright (C) 2024-2025 Intel Corporation
5-
>>>>>>> dell-deploy-1.4-nv
62
# SPDX-License-Identifier: Apache-2.0
73

84
deploy_inference_llm_models_playbook() {
@@ -14,10 +10,7 @@ deploy_inference_llm_models_playbook() {
1410
cpu_playbook="true"
1511
gpu_playbook="false"
1612
gaudi_deployment="false"
17-
<<<<<<< HEAD
18-
=======
1913
nvidia_deployment="false"
20-
>>>>>>> dell-deploy-1.4-nv
2114
enable_cpu_balloons="true" # Enable NRI balloons for CPU deployments
2215
huggingface_model_deployment_name="${huggingface_model_deployment_name}-cpu"
2316
if [ "$balloon_policy_cpu" == "enabled" ]; then
@@ -27,17 +20,13 @@ deploy_inference_llm_models_playbook() {
2720
if [ "$cpu_or_gpu" == "g" ]; then
2821
cpu_playbook="false"
2922
gpu_playbook="true"
30-
<<<<<<< HEAD
31-
gaudi_deployment="true"
32-
=======
3323
if [ "$gpu_vendor" == "nvidia" ]; then
3424
gaudi_deployment="false"
3525
nvidia_deployment="true"
3626
else
3727
gaudi_deployment="true"
3828
nvidia_deployment="false"
3929
fi
40-
>>>>>>> dell-deploy-1.4-nv
4130
enable_cpu_balloons="false"
4231
fi
4332
if [ "$deploy_apisix" == "no" ]; then
@@ -61,19 +50,13 @@ deploy_inference_llm_models_playbook() {
6150
elif [[ "$gaudi_platform" == "gaudi3" ]]; then
6251
gaudi_values_file=$gaudi3_values_file_path
6352
fi
64-
<<<<<<< HEAD
65-
=======
6653
nvidia_values_file=$nvidia_values_file_path
67-
>>>>>>> dell-deploy-1.4-nv
6854

6955
echo "Ingress based Deployment: $ingress_enabled"
7056
echo "APISIX Enabled: $apisix_enabled"
7157
echo "Keycloak Enabled: $deploy_keycloak"
7258
echo "Gaudi based: $gaudi_deployment"
73-
<<<<<<< HEAD
74-
=======
7559
echo "NVIDIA based: $nvidia_deployment"
76-
>>>>>>> dell-deploy-1.4-nv
7760
echo "Model Metrics Enabled: $vllm_metrics_enabled"
7861
echo "CPU NRI Balloons: $enable_cpu_balloons"
7962

@@ -103,11 +86,7 @@ deploy_inference_llm_models_playbook() {
10386
fi
10487

10588
ansible-playbook -i "${INVENTORY_PATH}" playbooks/deploy-inference-models.yml \
106-
<<<<<<< HEAD
107-
--extra-vars "kubernetes_platform=${kubernetes_platform} secret_name=${cluster_url} cert_file=${cert_file} key_file=${key_file} keycloak_admin_user=${keycloak_admin_user} keycloak_admin_password=${keycloak_admin_password} keycloak_client_id=${keycloak_client_id} hugging_face_token=${hugging_face_token} install_true=${install_true} model_name_list='${model_name_list//\ /,}' cpu_playbook=${cpu_playbook} gpu_playbook=${gpu_playbook} hugging_face_token_falcon3=${hugging_face_token_falcon3} deploy_keycloak=${deploy_keycloak} apisix_enabled=${apisix_enabled} ingress_enabled=${ingress_enabled} gaudi_deployment=${gaudi_deployment} huggingface_model_id=${huggingface_model_id} hugging_face_model_deployment=${hugging_face_model_deployment} huggingface_model_deployment_name=${huggingface_model_deployment_name} deploy_inference_llm_models_playbook=${deploy_inference_llm_models_playbook} huggingface_tensor_parellel_size=${huggingface_tensor_parellel_size} deploy_genai_gateway=${deploy_genai_gateway} vllm_metrics_enabled=${vllm_metrics_enabled} gaudi_values_file=${gaudi_values_file} xeon_values_file=${xeon_values_file_path} deploy_ceph=${deploy_ceph} enable_cpu_balloons=${enable_cpu_balloons} balloon_policy_cpu=${balloon_policy_cpu} aws_certificate_arn=${aws_certificate_arn}" --tags "$tags" --vault-password-file "$vault_pass_file"
108-
=======
10989
--extra-vars "kubernetes_platform=${kubernetes_platform} secret_name=${cluster_url} cert_file=${cert_file} key_file=${key_file} keycloak_admin_user=${keycloak_admin_user} keycloak_admin_password=${keycloak_admin_password} keycloak_client_id=${keycloak_client_id} hugging_face_token=${hugging_face_token} install_true=${install_true} model_name_list='${model_name_list//\ /,}' cpu_playbook=${cpu_playbook} gpu_playbook=${gpu_playbook} hugging_face_token_falcon3=${hugging_face_token_falcon3} deploy_keycloak=${deploy_keycloak} apisix_enabled=${apisix_enabled} ingress_enabled=${ingress_enabled} gaudi_deployment=${gaudi_deployment} nvidia_deployment=${nvidia_deployment} huggingface_model_id=${huggingface_model_id} hugging_face_model_deployment=${hugging_face_model_deployment} huggingface_model_deployment_name=${huggingface_model_deployment_name} deploy_inference_llm_models_playbook=${deploy_inference_llm_models_playbook} huggingface_tensor_parellel_size=${huggingface_tensor_parellel_size} deploy_genai_gateway=${deploy_genai_gateway} vllm_metrics_enabled=${vllm_metrics_enabled} gaudi_values_file=${gaudi_values_file} nvidia_values_file=${nvidia_values_file} xeon_values_file=${xeon_values_file_path} deploy_ceph=${deploy_ceph} enable_cpu_balloons=${enable_cpu_balloons} balloon_policy_cpu=${balloon_policy_cpu} aws_certificate_arn=${aws_certificate_arn}" --tags "$tags" --vault-password-file "$vault_pass_file"
110-
>>>>>>> dell-deploy-1.4-nv
11190

11291
}
11392

@@ -138,27 +117,7 @@ add_model() {
138117
setup_bastion "$@"
139118
INVENTORY_PATH=$brownfield_deployment_host_file
140119
fi
141-
<<<<<<< HEAD
142-
invoke_prereq_workflows "$@"
143-
144-
# Deploy NRI CPU Balloons for CPU deployments (after all infrastructure, before models)
145-
if [[ "$deploy_nri_balloon_policy" == "yes" ]]; then
146-
# Ensure this is a CPU deployment
147-
if [[ "$cpu_or_gpu" != "c" ]]; then
148-
echo "${RED}Error: NRI Balloon Policy can only be deployed for CPU deployments (cpu_or_gpu='c')${NC}"
149-
echo "${RED}Current cpu_or_gpu setting: '$cpu_or_gpu'${NC}"
150-
echo "${RED}Please set cpu_or_gpu to 'c' or disable NRI balloon policy deployment. Exiting!${NC}"
151-
exit 1
152-
fi
153-
execute_and_check "Deploying CPU Optimization (NRI Balloons & Topology Detection)..." deploy_nri_balloons_playbook "$@" \
154-
"CPU optimization deployed successfully." \
155-
"Failed to deploy CPU optimization. Exiting!."
156-
else
157-
echo "Skipping CPU optimization deployment..."
158-
fi
159-
=======
160120
invoke_prereq_workflows "$@"
161-
>>>>>>> dell-deploy-1.4-nv
162121
execute_and_check "Deploying Inference LLM Models..." deploy_inference_llm_models_playbook "$@" \
163122
"Inference LLM Model is deployed successfully." \
164123
"Failed to deploy Inference LLM Model Exiting!."
@@ -175,8 +134,4 @@ add_model() {
175134
echo "Please refer to this comprehensive guide for detailed instructions."
176135
echo ""
177136
fi
178-
<<<<<<< HEAD
179-
}
180-
=======
181137
}
182-
>>>>>>> dell-deploy-1.4-nv

‎core/lib/models/model-selection.sh‎

Lines changed: 0 additions & 18 deletions
Original file line numberDiff line numberDiff line change
@@ -1,8 +1,4 @@
1-
<<<<<<< HEAD
21
# Copyright (C) 2025-2026 Intel Corporation
3-
=======
4-
# Copyright (C) 2024-2025 Intel Corporation
5-
>>>>>>> dell-deploy-1.4-nv
62
# SPDX-License-Identifier: Apache-2.0
73

84
model_selection(){
@@ -44,19 +40,12 @@ model_selection(){
4440
echo "12. BAAI/bge-reranker-base"
4541
echo "13. codellama/CodeLlama-34b-Instruct-hf"
4642
echo "14. tiiuae/Falcon3-7B-Instruct"
47-
<<<<<<< HEAD
48-
=======
4943
echo "15. meta-llama/Llama-3.2-3B-Instruct"
50-
>>>>>>> dell-deploy-1.4-nv
5144
read -p "Enter the numbers of the GPU models you want to deploy/remove (comma-separated, e.g., 1,3,5): " models
5245
# Validate input
5346
IFS=',' read -ra selected <<< "$models"
5447
for m in "${selected[@]}"; do
55-
<<<<<<< HEAD
56-
if ! [[ "$m" =~ ^(1|2|3|4|5|6|7|8|9|10|11|12|13|14)$ ]]; then
57-
=======
5848
if ! [[ "$m" =~ ^(1|2|3|4|5|6|7|8|9|10|11|12|13|14|15)$ ]]; then
59-
>>>>>>> dell-deploy-1.4-nv
6049
echo "Error: Invalid model selected ($m). Exiting." >&2
6150
exit 1
6251
fi
@@ -212,16 +201,13 @@ get_model_names() {
212201
fi
213202
model_names+=("falcon3-7b")
214203
;;
215-
<<<<<<< HEAD
216-
=======
217204
15)
218205
if [ "$cpu_or_gpu" = "c" ]; then
219206
echo "Error: GPU model identifier provided for CPU deployment/removal." >&2
220207
exit 1
221208
fi
222209
model_names+=("llama-3-2-3b")
223210
;;
224-
>>>>>>> dell-deploy-1.4-nv
225211
21)
226212
if [ "$cpu_or_gpu" = "g" ]; then
227213
echo "Error: CPU model identifier provided for GPU deployment/removal." >&2
@@ -264,11 +250,7 @@ get_model_names() {
264250
fi
265251
model_names+=("cpu-qwen3-4b")
266252
;;
267-
<<<<<<< HEAD
268-
"llama-8b"|"llama-70b"|"codellama-34b"|"mixtral-8x-7b"|"mistral-7b"|"tei"|"tei-rerank"|"falcon3-7b"|"deepseek-r1-distill-qwen-32b"|"deepseek-r1-distill-llama8b"|"llama3-405b"|"llama-3-3-70b"|"llama-4-scout-17b"|"qwen-2-5-32b")
269-
=======
270253
"llama-8b"|"llama-70b"|"codellama-34b"|"mixtral-8x-7b"|"mistral-7b"|"tei"|"tei-rerank"|"falcon3-7b"|"deepseek-r1-distill-qwen-32b"|"deepseek-r1-distill-llama8b"|"llama3-405b"|"llama-3-3-70b"|"llama-4-scout-17b"|"qwen-2-5-32b"|"llama-3-2-3b")
271-
>>>>>>> dell-deploy-1.4-nv
272254
if [ "$cpu_or_gpu" = "c" ]; then
273255
echo "Error: GPU model identifier provided for CPU deployment/removal." >&2
274256
exit 1

‎core/lib/system/config-vars.sh‎

Lines changed: 0 additions & 15 deletions
Original file line numberDiff line numberDiff line change
@@ -1,18 +1,11 @@
1-
<<<<<<< HEAD
21
# Copyright (C) 2025-2026 Intel Corporation
3-
=======
4-
# Copyright (C) 2024-2025 Intel Corporation
5-
>>>>>>> dell-deploy-1.4-nv
62
# SPDX-License-Identifier: Apache-2.0
73

84
HOMEDIR="$(pwd)"
95
KUBESPRAYDIR="$(dirname "$(realpath "$0")")/kubespray"
106
VENVDIR="$(dirname "$(realpath "$0")")/kubespray225-venv"
117
INVENTORY_PATH="${KUBESPRAYDIR}/inventory/mycluster/hosts.yaml"
12-
<<<<<<< HEAD
13-
=======
148
BECOME_PASSWORD_FILE="$(dirname "$(realpath "$0")")/inventory/.become-passfile"
15-
>>>>>>> dell-deploy-1.4-nv
169
# Set the default values for the parameters
1710
cluster_url=""
1811
cert_file=""
@@ -24,15 +17,10 @@ hugging_face_token=""
2417
models=""
2518
model_name_list=""
2619
cpu_or_gpu=""
27-
<<<<<<< HEAD
28-
deploy_kubernetes_fresh=""
29-
deploy_habana_ai_operator=""
30-
=======
3120
gpu_vendor=""
3221
deploy_kubernetes_fresh=""
3322
deploy_habana_ai_operator=""
3423
deploy_nvidia_operator=""
35-
>>>>>>> dell-deploy-1.4-nv
3624
deploy_ingress_controller=""
3725
deploy_genai_gateway=""
3826
deploy_llm_models=""
@@ -58,10 +46,7 @@ gaudi_platform=""
5846
gaudi_operator=""
5947
gaudi2_values_file_path=""
6048
gaudi3_values_file_path=""
61-
<<<<<<< HEAD
62-
=======
6349
nvidia_values_file_path=""
64-
>>>>>>> dell-deploy-1.4-nv
6550
python3_interpreter=""
6651
skip_check=""
6752
purge_inference_cluster=""

0 commit comments

Comments
 (0)