Add comprehensive Podman support alongside Docker instructions

- Add Podman installation and deployment instructions in separate source blocks
- Update container deployment sections to include both Docker and Podman examples
- Add Podman Compose alternatives for all Docker Compose configurations
- Include proper GPU device syntax for Podman (--device nvidia.com/gpu=all)
- Maintain separate configuration files for Docker and Podman compose setups

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

Author: blues-man

documentation/modules/ROOT/pages/01-setup.adoc

@@ -79,10 +79,12 @@ cd vllm
 pip install -e .
 ----
 
-=== Method 4: Docker Installation
+=== Method 4: Container Installation
 
 For containerized deployment:
 
+**Docker:**
+
 [.console-input]
 [source,bash,subs="+macros,+attributes"]
 ----
@@ -96,6 +98,21 @@ docker run --gpus all \
     --model microsoft/DialoGPT-medium
 ----
 
+**Podman:**
+
+[.console-input]
+[source,bash,subs="+macros,+attributes"]
+----
+# Pull the official vLLM image
+podman pull vllm/vllm-openai:latest
+
+# Run with GPU support
+podman run --device nvidia.com/gpu=all \
+    -p 8000:8000 \
+    vllm/vllm-openai:latest \
+    --model microsoft/DialoGPT-medium
+----
+
 [#verification]
 == Verify Installation
 

documentation/modules/ROOT/pages/02-deploy.adoc

@@ -179,11 +179,13 @@ curl http://localhost:8000/v1/completions \
 ----
 
 [#docker]
-== Docker Deployment
+== Container Deployment
 
-For production deployments, Docker provides a convenient way to run vLLM:
+For production deployments, containers provide a convenient way to run vLLM:
 
-=== Basic Docker Setup
+=== Basic Container Setup
+
+**Docker:**
 
 [.console-input]
 [source,bash,subs="+macros,+attributes"]
@@ -201,7 +203,27 @@ docker run --gpus all \
     --port 8000
 ----
 
-=== Docker Compose
+**Podman:**
+
+[.console-input]
+[source,bash,subs="+macros,+attributes"]
+----
+# Pull the official image
+podman pull vllm/vllm-openai:latest
+
+# Run with GPU support
+podman run --device nvidia.com/gpu=all \
+    -p 8000:8000 \
+    -v ~/.cache/huggingface:/root/.cache/huggingface \
+    vllm/vllm-openai:latest \
+    --model microsoft/DialoGPT-medium \
+    --host 0.0.0.0 \
+    --port 8000
+----
+
+=== Container Compose
+
+**Docker Compose:**
 
 Create a `docker-compose.yml` file:
 
@@ -238,6 +260,38 @@ Then run:
 docker-compose up -d
 ----
 
+**Podman Compose:**
+
+Create a `podman-compose.yml` file:
+
+[.console-input]
+[source,yaml,subs="+macros,+attributes"]
+----
+version: '3.8'
+services:
+  vllm:
+    image: vllm/vllm-openai:latest
+    ports:
+      - "8000:8000"
+    volumes:
+      - ~/.cache/huggingface:/root/.cache/huggingface
+    command: >
+      --model microsoft/DialoGPT-medium
+      --host 0.0.0.0
+      --port 8000
+      --tensor-parallel-size 1
+    devices:
+      - nvidia.com/gpu=all
+----
+
+Then run:
+
+[.console-input]
+[source,bash,subs="+macros,+attributes"]
+----
+podman-compose up -d
+----
+
 [#monitoring]
 == Monitoring and Health Checks
 

documentation/modules/ROOT/pages/03-advanced.adoc

@@ -365,6 +365,8 @@ if __name__ == "__main__":
 
 Deploy multiple vLLM instances behind a load balancer:
 
+**Docker Compose:**
+
 [.console-input]
 [source,yaml,subs="+macros,+attributes"]
 ----
@@ -414,6 +416,47 @@ services:
       - vllm-node-2
 ----
 
+**Podman Compose:**
+
+[.console-input]
+[source,yaml,subs="+macros,+attributes"]
+----
+# podman-compose-cluster.yml
+version: '3.8'
+services:
+  vllm-node-1:
+    image: vllm/vllm-openai:latest
+    ports:
+      - "8001:8000"
+    command: >
+      --model microsoft/DialoGPT-medium
+      --host 0.0.0.0
+      --port 8000
+    devices:
+      - nvidia.com/gpu=0
+
+  vllm-node-2:
+    image: vllm/vllm-openai:latest
+    ports:
+      - "8002:8000"
+    command: >
+      --model microsoft/DialoGPT-medium
+      --host 0.0.0.0
+      --port 8000
+    devices:
+      - nvidia.com/gpu=1
+
+  nginx:
+    image: nginx:alpine
+    ports:
+      - "8000:80"
+    volumes:
+      - ./nginx.conf:/etc/nginx/nginx.conf
+    depends_on:
+      - vllm-node-1
+      - vllm-node-2
+----
+
 === Load Balancer Configuration
 
 Create `nginx.conf`: