Update default port from 5000 -> 8321

distributions/bedrock/compose.yaml

@@ -5,7 +5,7 @@ services:
       - ~/.llama:/root/.llama
       - ./run.yaml:/root/llamastack-run-bedrock.yaml
     ports:
-      - "5000:5000"
+      - "8321:8321"
     entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-bedrock.yaml"
     deploy:
       restart_policy:

distributions/cerebras/compose.yaml

@@ -6,7 +6,7 @@ services:
       - ~/.llama:/root/.llama
       - ./run.yaml:/root/llamastack-run-cerebras.yaml
     ports:
-      - "5000:5000"
+      - "8321:8321"
     entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-cerebras.yaml"
     deploy:
       restart_policy:

distributions/dell-tgi/compose.yaml

@@ -40,7 +40,7 @@ services:
       # Link to TGI run.yaml file
       - ./run.yaml:/root/my-run.yaml
     ports:
-      - "5000:5000"
+      - "8321:8321"
     # Hack: wait for TGI server to start before starting docker
     entrypoint: bash -c "sleep 60; python -m llama_stack.distribution.server.server --yaml_config /root/my-run.yaml"
     restart_policy:

distributions/fireworks/compose.yaml

@@ -6,7 +6,7 @@ services:
       - ~/.llama:/root/.llama
       - ./run.yaml:/root/llamastack-run-fireworks.yaml
     ports:
-      - "5000:5000"
+      - "8321:8321"
     entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-fireworks.yaml"
     deploy:
       restart_policy:

distributions/meta-reference-gpu/compose.yaml

@@ -6,7 +6,7 @@ services:
       - ~/.llama:/root/.llama
       - ./run.yaml:/root/my-run.yaml
     ports:
-      - "5000:5000"
+      - "8321:8321"
     devices:
       - nvidia.com/gpu=all
     environment:

distributions/meta-reference-quantized-gpu/compose.yaml

@@ -6,7 +6,7 @@ services:
       - ~/.llama:/root/.llama
       - ./run.yaml:/root/my-run.yaml
     ports:
-      - "5000:5000"
+      - "8321:8321"
     devices:
       - nvidia.com/gpu=all
     environment:

distributions/remote-nvidia/compose.yaml

@@ -6,7 +6,7 @@ services:
       - ~/.llama:/root/.llama
       - ./run.yaml:/root/llamastack-run-nvidia.yaml
     ports:
-      - "5000:5000"
+      - "8321:8321"
     environment:
       - INFERENCE_MODEL=${INFERENCE_MODEL:-Llama3.1-8B-Instruct}
       - NVIDIA_API_KEY=${NVIDIA_API_KEY:-}

distributions/together/compose.yaml

@@ -6,7 +6,7 @@ services:
       - ~/.llama:/root/.llama
       - ./run.yaml:/root/llamastack-run-together.yaml
     ports:
-      - "5000:5000"
+      - "8321:8321"
     entrypoint: bash -c "python -m llama_stack.distribution.server.server --yaml_config /root/llamastack-run-together.yaml"
     deploy:
       restart_policy:

distributions/vllm-gpu/compose.yaml

@@ -6,7 +6,7 @@ services:
       - ~/.llama:/root/.llama
       - ./run.yaml:/root/my-run.yaml
     ports:
-      - "5000:5000"
+      - "8321:8321"
     devices:
       - nvidia.com/gpu=all
     environment: