Fix Phase 1 server validation defects

ansible/roles/vllm/tasks/main.yml

@@ -22,7 +22,7 @@
   when: gpu_check.stdout == "" or gpu_check.rc != 0
 
 - name: Pull vLLM Docker image
-  shell: docker pull vllm/vllm-openai:latest
+  shell: docker pull vllm/vllm-openai:v0.10.2
   retries: 3
   delay: 15
   when: gpu_check.stdout != "" and gpu_check.rc == 0
@@ -53,12 +53,11 @@
         -p 8000:8000 \
         -v /opt/cezen/models:/root/.cache/huggingface \
         -e HF_HOME=/root/.cache/huggingface \
-        vllm/vllm-openai:latest \
+        vllm/vllm-openai:v0.10.2 \
         --model {{ vllm_model }} \
         --gpu-memory-utilization {{ vllm_gpu_memory_util }} \
         --max-model-len {{ vllm_max_model_len }} \
-        --tensor-parallel-size {{ vllm_tensor_parallel }} \
-        {{ vllm_quant_flag }}
+        --tensor-parallel-size {{ vllm_tensor_parallel }}{{ ' ' + vllm_quant_flag if vllm_quant_flag else '' }}
       ExecStop=/usr/bin/docker stop vllm
       TimeoutStartSec=300
 
@@ -92,5 +91,6 @@
   systemd:
     name: vllm
     enabled: true
+    state: started
     daemon_reload: true
   when: gpu_check.stdout != "" and gpu_check.rc == 0