rename LLAMASTACK_PORT to LLAMA_STACK_PORT for consistency with other env vars (#744)

# What does this PR do?

Rename environment var for consistency

## Test Plan

No regressions

## Sources

## Before submitting

- [X] This PR fixes a typo or improves the docs (you can dismiss the
other checks if that's the case).
- [X] Ran pre-commit to handle lint / formatting issues.
- [X] Read the [contributor
guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md),
Pull Request section?
- [X] Updated relevant documentation.
- [ ] Wrote necessary unit or integration tests.

---------

Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
Co-authored-by: Yuan Tang <terrytangyuan@gmail.com>

llama_stack/cli/stack/run.py

@@ -35,7 +35,7 @@ class StackRun(Subcommand):
             "--port",
             type=int,
             help="Port to run the server on. Defaults to 5000",
-            default=int(os.getenv("LLAMASTACK_PORT", 5000)),
+            default=int(os.getenv("LLAMA_STACK_PORT", 5000)),
         )
         self.parser.add_argument(
             "--disable-ipv6",

llama_stack/distribution/server/server.py

@@ -290,7 +290,7 @@ def main():
     parser.add_argument(
         "--port",
         type=int,
-        default=int(os.getenv("LLAMASTACK_PORT", 5000)),
+        default=int(os.getenv("LLAMA_STACK_PORT", 5000)),
         help="Port to listen on",
     )
     parser.add_argument(

llama_stack/distribution/start_container.sh

@@ -90,6 +90,6 @@ $DOCKER_BINARY run $DOCKER_OPTS -it \
   $env_vars \
   -v "$yaml_config:/app/config.yaml" \
   $mounts \
-  --env LLAMASTACK_PORT=$port \
+  --env LLAMA_STACK_PORT=$port \
   --entrypoint='["python", "-m", "llama_stack.distribution.server.server", "--yaml-config", "/app/config.yaml"]' \
   $docker_image:$version_tag

llama_stack/templates/bedrock/bedrock.py

@@ -84,7 +84,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

llama_stack/templates/cerebras/cerebras.py

@@ -102,7 +102,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

llama_stack/templates/fireworks/fireworks.py

@@ -114,7 +114,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

llama_stack/templates/hf-endpoint/hf_endpoint.py

@@ -126,7 +126,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

llama_stack/templates/hf-serverless/hf_serverless.py

@@ -126,7 +126,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

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

@@ -132,7 +132,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

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

@@ -99,7 +99,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

llama_stack/templates/ollama/ollama.py

@@ -120,7 +120,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

llama_stack/templates/remote-vllm/vllm.py

@@ -125,7 +125,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

llama_stack/templates/tgi/tgi.py

@@ -127,7 +127,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

llama_stack/templates/together/together.py

@@ -112,7 +112,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),

llama_stack/templates/vllm-gpu/vllm.py

@@ -99,7 +99,7 @@ def get_distribution_template() -> DistributionTemplate:
             ),
         },
         run_config_env_vars={
-            "LLAMASTACK_PORT": (
+            "LLAMA_STACK_PORT": (
                 "5001",
                 "Port for the Llama Stack distribution server",
             ),