Merge branch 'main' into add-watsonx-inference-adapter

llama_stack/templates/bedrock/run.yaml

@@ -39,6 +39,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/bedrock/trace_store.db}
   eval:

llama_stack/templates/cerebras/run.yaml

@@ -79,6 +79,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/cerebras/trace_store.db}
   tool_runtime:

llama_stack/templates/ci-tests/run.yaml

@@ -42,6 +42,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ci-tests/trace_store.db}
   eval:

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

@@ -45,6 +45,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dell/trace_store.db}
   eval:

llama_stack/templates/dell/run.yaml

@@ -41,6 +41,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dell/trace_store.db}
   eval:

llama_stack/templates/dev/run.yaml

@@ -71,6 +71,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dev/trace_store.db}
   eval:

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

@@ -50,6 +50,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/fireworks/trace_store.db}
   eval:

llama_stack/templates/fireworks/run.yaml

@@ -45,6 +45,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/fireworks/trace_store.db}
   eval:

llama_stack/templates/groq/run.yaml

@@ -45,6 +45,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/groq/trace_store.db}
   eval:

llama_stack/templates/hf-endpoint/run-with-safety.yaml

@@ -50,6 +50,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-endpoint/trace_store.db}
   eval:

llama_stack/templates/hf-endpoint/run.yaml

@@ -45,6 +45,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-endpoint/trace_store.db}
   eval:

llama_stack/templates/hf-serverless/run-with-safety.yaml

@@ -50,6 +50,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-serverless/trace_store.db}
   eval:

llama_stack/templates/hf-serverless/run.yaml

@@ -45,6 +45,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-serverless/trace_store.db}
   eval:

llama_stack/templates/meta-reference-gpu/run-with-safety.yaml

@@ -52,6 +52,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-gpu/trace_store.db}
   eval:

llama_stack/templates/meta-reference-gpu/run.yaml

@@ -46,6 +46,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-gpu/trace_store.db}
   eval:

llama_stack/templates/meta-reference-quantized-gpu/run.yaml

@@ -48,6 +48,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-quantized-gpu/trace_store.db}
   eval:

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/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"],
@@ -89,6 +90,31 @@ def get_distribution_template() -> DistributionTemplate:
                 "",
                 "NVIDIA API Key",
             ),
+            ## Nemo Customizer related variables
+            "NVIDIA_USER_ID": (
+                "llama-stack-user",
+                "NVIDIA User ID",
+            ),
+            "NVIDIA_DATASET_NAMESPACE": (
+                "default",
+                "NVIDIA Dataset Namespace",
+            ),
+            "NVIDIA_ACCESS_POLICIES": (
+                "{}",
+                "NVIDIA Access Policies",
+            ),
+            "NVIDIA_PROJECT_ID": (
+                "test-project",
+                "NVIDIA Project ID",
+            ),
+            "NVIDIA_CUSTOMIZER_URL": (
+                "https://customizer.api.nvidia.com",
+                "NVIDIA Customizer URL",
+            ),
+            "NVIDIA_OUTPUT_MODEL_DIR": (
+                "test-example-model@v1",
+                "NVIDIA Output Model Directory",
+            ),
             "GUARDRAILS_SERVICE_URL": (
                 "http://0.0.0.0:7331",
                 "URL for the NeMo Guardrails Service",

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

@@ -5,6 +5,7 @@ apis:
 - datasetio
 - eval
 - inference
+- post_training
 - safety
 - scoring
 - telemetry
@@ -48,6 +49,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
   eval:
@@ -58,6 +60,14 @@ 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
@@ -43,6 +44,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/nvidia/trace_store.db}
   eval:
@@ -53,6 +55,14 @@ 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/ollama/run-with-safety.yaml

@@ -43,6 +43,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ollama/trace_store.db}
   eval:

llama_stack/templates/ollama/run.yaml

@@ -41,6 +41,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ollama/trace_store.db}
   eval:

llama_stack/templates/open-benchmark/run.yaml

@@ -68,6 +68,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/open-benchmark/trace_store.db}
   eval:

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

@@ -50,6 +50,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/passthrough/trace_store.db}
   eval:

llama_stack/templates/passthrough/run.yaml

@@ -45,6 +45,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/passthrough/trace_store.db}
   eval:

llama_stack/templates/remote-vllm/run-with-safety.yaml

@@ -88,6 +88,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
   tool_runtime:

llama_stack/templates/remote-vllm/run.yaml

@@ -81,6 +81,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
   tool_runtime:

llama_stack/templates/sambanova/run.yaml

@@ -51,6 +51,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/sambanova/trace_store.db}
   tool_runtime:

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

@@ -45,6 +45,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/tgi/trace_store.db}
   eval:

llama_stack/templates/tgi/run.yaml

@@ -44,6 +44,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/tgi/trace_store.db}
   eval:

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

@@ -50,6 +50,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/together/trace_store.db}
   eval:

llama_stack/templates/together/run.yaml

@@ -45,6 +45,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/together/trace_store.db}
   eval:

llama_stack/templates/vllm-gpu/run.yaml

@@ -49,6 +49,7 @@ providers:
   - provider_id: meta-reference
     provider_type: inline::meta-reference
     config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
       sinks: ${env.TELEMETRY_SINKS:console,sqlite}
       sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/vllm-gpu/trace_store.db}
   eval: