Merge branch 'main' of https://github.com/meta-llama/llama-stack into add_nemo_customizer

llama_stack/templates/nvidia/build.yaml

@@ -14,6 +14,8 @@ distribution_spec:
     - inline::meta-reference
     eval:
     - inline::meta-reference
+    post_training:
+    - remote::nvidia
     datasetio:
     - inline::localfs
     scoring:

llama_stack/templates/nvidia/doc_template.md

@@ -39,9 +39,10 @@ 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 \
   -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
   -v ./run.yaml:/root/my-run.yaml \
   llamastack/distribution-{{ name }} \
@@ -55,7 +56,7 @@ docker run \
 ```bash
 llama stack build --template nvidia --image-type conda
 llama stack run ./run.yaml \
-  --port 5001 \
+  --port 8321 \
   --env NVIDIA_API_KEY=$NVIDIA_API_KEY
   --env INFERENCE_MODEL=$INFERENCE_MODEL
 ```

llama_stack/templates/nvidia/nvidia.py

@@ -21,6 +21,7 @@ def get_distribution_template() -> DistributionTemplate:
         "agents": ["inline::meta-reference"],
         "telemetry": ["inline::meta-reference"],
         "eval": ["inline::meta-reference"],
+        "post_training": ["remote::nvidia"],
         "datasetio": ["inline::localfs"],
         "scoring": ["inline::basic"],
         "tool_runtime": ["inline::rag-runtime"],

llama_stack/templates/nvidia/run-with-safety.yaml

@@ -5,6 +5,7 @@ apis:
 - datasetio
 - eval
 - inference
+- post_training
 - safety
 - scoring
 - telemetry
@@ -48,7 +49,6 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
-      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
   eval:
@@ -59,6 +59,14 @@ providers:
         type: sqlite
         namespace: null
         db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/meta_reference_eval.db
+  post_training:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:default}
+      project_id: ${env.NVIDIA_PROJECT_ID:test-project}
+      customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:http://nemo.test}
   datasetio:
   - provider_id: localfs
     provider_type: inline::localfs

llama_stack/templates/nvidia/run.yaml

@@ -5,6 +5,7 @@ apis:
 - datasetio
 - eval
 - inference
+- post_training
 - safety
 - scoring
 - telemetry
@@ -43,7 +44,6 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
-      service_name: ${env.OTEL_SERVICE_NAME:llama-stack}
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
   eval:
@@ -54,6 +54,14 @@ providers:
         type: sqlite
         namespace: null
         db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/nvidia}/meta_reference_eval.db
+  post_training:
+  - provider_id: nvidia
+    provider_type: remote::nvidia
+    config:
+      api_key: ${env.NVIDIA_API_KEY:}
+      dataset_namespace: ${env.NVIDIA_DATASET_NAMESPACE:default}
+      project_id: ${env.NVIDIA_PROJECT_ID:test-project}
+      customizer_url: ${env.NVIDIA_CUSTOMIZER_URL:http://nemo.test}
   datasetio:
   - provider_id: localfs
     provider_type: inline::localfs