fix: Default to port 8321 everywhere (#1734)

As titled, moved all instances of 5001 to 8321

llama_stack/templates/meta-reference-gpu/doc_template.md

@@ -65,7 +65,7 @@ You can do this via Conda (build code) or Docker which has a pre-built image.
 This method allows you to get started quickly without having to build the distribution code.
 
 ```bash
-LLAMA_STACK_PORT=5001
+LLAMA_STACK_PORT=8321
 docker run \
   -it \
   --pull always \
@@ -97,7 +97,7 @@ Make sure you have done `uv pip install llama-stack` and have the Llama Stack CL
 ```bash
 llama stack build --template {{ name }} --image-type conda
 llama stack run distributions/{{ name }}/run.yaml \
-  --port 5001 \
+  --port 8321 \
   --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 ```
 
@@ -105,7 +105,7 @@ If you are using Llama Stack Safety / Shield APIs, use:
 
 ```bash
 llama stack run distributions/{{ name }}/run-with-safety.yaml \
-  --port 5001 \
+  --port 8321 \
   --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
   --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 ```

llama_stack/templates/meta-reference-gpu/meta_reference.py

@@ -134,7 +134,7 @@ def get_distribution_template() -> DistributionTemplate:
         },
         run_config_env_vars={
             "LLAMA_STACK_PORT": (
-                "5001",
+                "8321",
                 "Port for the Llama Stack distribution server",
             ),
             "INFERENCE_MODEL": (