Merge branch 'main' into feat/litellm_sambanova_usage

2025-12-30 01:09:32 +00:00 · 2025-04-01 07:57:21 -05:00 · 2025-04-01 07:57:21 -05:00 · 9c9f9577e2
commit 9c9f9577e2
parent 8783dd8162 19f504e9e2
173 changed files with 3073 additions and 3118 deletions
--- a/llama_stack/templates/bedrock/run.yaml
+++ b/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: ${env.SQLITE_DB_PATH:~/.llama/distributions/bedrock/trace_store.db}
  eval:
--- a/llama_stack/templates/cerebras/run.yaml
+++ b/llama_stack/templates/cerebras/run.yaml
@ -79,6 +79,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/cerebras/trace_store.db}
  tool_runtime:
--- a/llama_stack/templates/ci-tests/run.yaml
+++ b/llama_stack/templates/ci-tests/run.yaml
@ -42,6 +42,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ci-tests/trace_store.db}
  eval:
--- a/llama_stack/templates/dell/run-with-safety.yaml
+++ b/llama_stack/templates/dell/run-with-safety.yaml
@ -45,6 +45,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/dell/trace_store.db}
  eval:
--- a/llama_stack/templates/dell/run.yaml
+++ b/llama_stack/templates/dell/run.yaml
@ -41,6 +41,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${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:
--- a/llama_stack/templates/dependencies.json
+++ b/llama_stack/templates/dependencies.json
@ -0,0 +1,770 @@
+{
+  "bedrock": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "boto3",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn"
+  ],
+  "cerebras": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "cerebras_cloud_sdk",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "ci-tests": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fastapi",
+    "fire",
+    "fireworks-ai",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlite-vec",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "dell": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "huggingface_hub",
+    "langdetect",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "dev": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fastapi",
+    "fire",
+    "fireworks-ai",
+    "httpx",
+    "langdetect",
+    "litellm",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlite-vec",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "fireworks": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "fireworks-ai",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "groq": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "litellm",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn"
+  ],
+  "hf-endpoint": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "huggingface_hub",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn"
+  ],
+  "hf-serverless": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "huggingface_hub",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "meta-reference-gpu": [
+    "accelerate",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fairscale",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "lm-format-enforcer",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentence-transformers",
+    "sentencepiece",
+    "torch",
+    "torchvision",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "zmq"
+  ],
+  "meta-reference-quantized-gpu": [
+    "accelerate",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fairscale",
+    "faiss-cpu",
+    "fastapi",
+    "fbgemm-gpu",
+    "fire",
+    "httpx",
+    "langdetect",
+    "lm-format-enforcer",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentence-transformers",
+    "sentencepiece",
+    "torch",
+    "torchao==0.5.0",
+    "torchvision",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "zmq"
+  ],
+  "nvidia": [
+    "aiohttp",
+    "aiosqlite",
+    "blobfile",
+    "chardet",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn"
+  ],
+  "ollama": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "ollama",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn"
+  ],
+  "open-benchmark": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "litellm",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "sqlite-vec",
+    "together",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn"
+  ],
+  "passthrough": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "remote-vllm": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "sambanova": [
+    "aiosqlite",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "litellm",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "tgi": [
+    "aiohttp",
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "huggingface_hub",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "together": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "together",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
+  "vllm-gpu": [
+    "aiosqlite",
+    "autoevals",
+    "blobfile",
+    "chardet",
+    "chromadb-client",
+    "datasets",
+    "emoji",
+    "faiss-cpu",
+    "fastapi",
+    "fire",
+    "httpx",
+    "langdetect",
+    "matplotlib",
+    "mcp",
+    "nltk",
+    "numpy",
+    "openai",
+    "opentelemetry-exporter-otlp-proto-http",
+    "opentelemetry-sdk",
+    "pandas",
+    "pillow",
+    "psycopg2-binary",
+    "pymongo",
+    "pypdf",
+    "pythainlp",
+    "redis",
+    "requests",
+    "scikit-learn",
+    "scipy",
+    "sentencepiece",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "vllm",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ]
+}
--- a/llama_stack/templates/dev/run.yaml
+++ b/llama_stack/templates/dev/run.yaml
@ -76,6 +76,7 @@ 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: ${env.SQLITE_DB_PATH:~/.llama/distributions/dev/trace_store.db}
  eval:
--- a/llama_stack/templates/fireworks/run-with-safety.yaml
+++ b/llama_stack/templates/fireworks/run-with-safety.yaml
@ -50,6 +50,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/fireworks/trace_store.db}
  eval:
--- a/llama_stack/templates/fireworks/run.yaml
+++ b/llama_stack/templates/fireworks/run.yaml
@ -45,6 +45,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/fireworks/trace_store.db}
  eval:
--- a/llama_stack/templates/groq/run.yaml
+++ b/llama_stack/templates/groq/run.yaml
@ -45,6 +45,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/groq/trace_store.db}
  eval:
--- a/llama_stack/templates/hf-endpoint/run-with-safety.yaml
+++ b/llama_stack/templates/hf-endpoint/run-with-safety.yaml
@ -50,6 +50,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-endpoint/trace_store.db}
  eval:
--- a/llama_stack/templates/hf-endpoint/run.yaml
+++ b/llama_stack/templates/hf-endpoint/run.yaml
@ -45,6 +45,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-endpoint/trace_store.db}
  eval:
--- a/llama_stack/templates/hf-serverless/run-with-safety.yaml
+++ b/llama_stack/templates/hf-serverless/run-with-safety.yaml
@ -50,6 +50,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-serverless/trace_store.db}
  eval:
--- a/llama_stack/templates/hf-serverless/run.yaml
+++ b/llama_stack/templates/hf-serverless/run.yaml
@ -45,6 +45,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/hf-serverless/trace_store.db}
  eval:
--- a/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
+++ b/llama_stack/templates/meta-reference-gpu/run-with-safety.yaml
@ -52,6 +52,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-gpu/trace_store.db}
  eval:
--- a/llama_stack/templates/meta-reference-gpu/run.yaml
+++ b/llama_stack/templates/meta-reference-gpu/run.yaml
@ -46,6 +46,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/meta-reference-gpu/trace_store.db}
  eval:
--- a/llama_stack/templates/meta-reference-quantized-gpu/run.yaml
+++ b/llama_stack/templates/meta-reference-quantized-gpu/run.yaml
@ -48,6 +48,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${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:
--- a/llama_stack/templates/nvidia/build.yaml
+++ b/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:
--- a/llama_stack/templates/nvidia/nvidia.py
+++ b/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",
--- a/llama_stack/templates/nvidia/run-with-safety.yaml
+++ b/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: ${env.NVIDIA_CUSTOMIZER_URL:http://nemo.test}
  datasetio:
  - provider_id: localfs
    provider_type: inline::localfs
--- a/llama_stack/templates/nvidia/run.yaml
+++ b/llama_stack/templates/nvidia/run.yaml
@ -5,6 +5,7 @@ apis:
 - datasetio
 - eval
 - inference
+- post_training
 - safety
 - scoring
 - telemetry
@ -43,6 +44,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${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: ${env.NVIDIA_CUSTOMIZER_URL:http://nemo.test}
  datasetio:
  - provider_id: localfs
    provider_type: inline::localfs
--- a/llama_stack/templates/ollama/run-with-safety.yaml
+++ b/llama_stack/templates/ollama/run-with-safety.yaml
@ -43,6 +43,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ollama/trace_store.db}
  eval:
--- a/llama_stack/templates/ollama/run.yaml
+++ b/llama_stack/templates/ollama/run.yaml
@ -41,6 +41,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/ollama/trace_store.db}
  eval:
--- a/llama_stack/templates/open-benchmark/run.yaml
+++ b/llama_stack/templates/open-benchmark/run.yaml
@ -68,6 +68,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/open-benchmark/trace_store.db}
  eval:
--- a/llama_stack/templates/passthrough/run-with-safety.yaml
+++ b/llama_stack/templates/passthrough/run-with-safety.yaml
@ -50,6 +50,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/passthrough/trace_store.db}
  eval:
--- a/llama_stack/templates/passthrough/run.yaml
+++ b/llama_stack/templates/passthrough/run.yaml
@ -45,6 +45,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${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:
--- a/llama_stack/templates/remote-vllm/doc_template.md
+++ b/llama_stack/templates/remote-vllm/doc_template.md
@ -85,11 +85,14 @@ export INFERENCE_PORT=8000
 export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
 export LLAMA_STACK_PORT=8321

+# You need a local checkout of llama-stack to run this, get it using
+# git clone https://github.com/meta-llama/llama-stack.git
+cd /path/to/llama-stack
+
 docker run \
-  -it \
  --pull always \
  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-  -v ./run.yaml:/root/my-run.yaml \
+  -v ./llama_stack/templates/remote-vllm/run.yaml:/root/my-run.yaml \
  llamastack/distribution-{{ name }} \
  --yaml-config /root/my-run.yaml \
  --port $LLAMA_STACK_PORT \
@ -108,7 +111,6 @@ export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
 cd /path/to/llama-stack

 docker run \
-  -it \
  --pull always \
  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
  -v ~/.llama:/root/.llama \
--- a/llama_stack/templates/remote-vllm/run-with-safety.yaml
+++ b/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: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
  tool_runtime:
--- a/llama_stack/templates/remote-vllm/run.yaml
+++ b/llama_stack/templates/remote-vllm/run.yaml
@ -81,6 +81,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/remote-vllm/trace_store.db}
  tool_runtime:
--- a/llama_stack/templates/sambanova/run.yaml
+++ b/llama_stack/templates/sambanova/run.yaml
@ -54,6 +54,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/sambanova/trace_store.db}
  tool_runtime:
--- a/llama_stack/templates/tgi/run-with-safety.yaml
+++ b/llama_stack/templates/tgi/run-with-safety.yaml
@ -45,6 +45,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/tgi/trace_store.db}
  eval:
--- a/llama_stack/templates/tgi/run.yaml
+++ b/llama_stack/templates/tgi/run.yaml
@ -44,6 +44,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/tgi/trace_store.db}
  eval:
--- a/llama_stack/templates/together/run-with-safety.yaml
+++ b/llama_stack/templates/together/run-with-safety.yaml
@ -50,6 +50,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/together/trace_store.db}
  eval:
--- a/llama_stack/templates/together/run.yaml
+++ b/llama_stack/templates/together/run.yaml
@ -45,6 +45,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/together/trace_store.db}
  eval:
--- a/llama_stack/templates/vllm-gpu/run.yaml
+++ b/llama_stack/templates/vllm-gpu/run.yaml
@ -49,6 +49,7 @@ providers:
  - provider_id: meta-reference
    provider_type: inline::meta-reference
    config:
+      service_name: "${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: