Merge branch 'main' into nvidia-e2e-notebook

llama_stack/templates/ci-tests/run.yaml

@@ -193,6 +193,26 @@ models:
   provider_id: fireworks
   provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
   model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  model_type: llm
 - metadata:
     embedding_dimension: 768
     context_length: 8192

llama_stack/templates/dependencies.json

@@ -356,6 +356,7 @@
     "fairscale",
     "faiss-cpu",
     "fastapi",
+    "fbgemm-gpu-genai==1.1.2",
     "fire",
     "httpx",
     "langdetect",
@@ -380,51 +381,7 @@
     "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",
+    "torchao==0.8.0",
     "torchvision",
     "tqdm",
     "transformers",
@@ -721,6 +678,45 @@
     "sentence-transformers --no-deps",
     "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
   ],
+  "verification": [
+    "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",
+    "tqdm",
+    "transformers",
+    "tree_sitter",
+    "uvicorn",
+    "sentence-transformers --no-deps",
+    "torch torchvision --index-url https://download.pytorch.org/whl/cpu"
+  ],
   "vllm-gpu": [
     "aiosqlite",
     "autoevals",

llama_stack/templates/dev/run.yaml

@@ -251,6 +251,26 @@ models:
   provider_id: fireworks
   provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
   model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  model_type: llm
 - metadata:
     embedding_dimension: 768
     context_length: 8192
@@ -356,6 +376,46 @@ models:
   provider_id: groq
   provider_model_id: groq/llama-3.2-3b-preview
   model_type: llm
+- metadata: {}
+  model_id: groq/llama-4-scout-17b-16e-instruct
+  provider_id: groq
+  provider_model_id: groq/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
+  provider_id: groq
+  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: groq
+  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: groq/llama-4-maverick-17b-128e-instruct
+  provider_id: groq
+  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
+  provider_id: groq
+  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: groq
+  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
+  model_type: llm
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2

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

@@ -205,6 +205,26 @@ models:
   provider_id: fireworks
   provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
   model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  model_type: llm
 - metadata:
     embedding_dimension: 768
     context_length: 8192

llama_stack/templates/fireworks/run.yaml

@@ -200,6 +200,26 @@ models:
   provider_id: fireworks
   provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
   model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: fireworks
+  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  model_type: llm
 - metadata:
     embedding_dimension: 768
     context_length: 8192

llama_stack/templates/groq/run.yaml

@@ -148,6 +148,46 @@ models:
   provider_id: groq
   provider_model_id: groq/llama-3.2-3b-preview
   model_type: llm
+- metadata: {}
+  model_id: groq/llama-4-scout-17b-16e-instruct
+  provider_id: groq
+  provider_model_id: groq/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
+  provider_id: groq
+  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: groq
+  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: groq/llama-4-maverick-17b-128e-instruct
+  provider_id: groq
+  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: groq
+  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
+  provider_id: groq
+  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: groq
+  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
+  model_type: llm
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2

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

@@ -16,8 +16,12 @@ providers:
     provider_type: inline::meta-reference
     config:
       model: ${env.INFERENCE_MODEL}
-      max_seq_len: 4096
       checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
+      quantization:
+        type: ${env.QUANTIZATION_TYPE:bf16}
+      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:0}
+      max_batch_size: ${env.MAX_BATCH_SIZE:1}
+      max_seq_len: ${env.MAX_SEQ_LEN:4096}
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}
@@ -25,8 +29,12 @@ providers:
     provider_type: inline::meta-reference
     config:
       model: ${env.SAFETY_MODEL}
-      max_seq_len: 4096
       checkpoint_dir: ${env.SAFETY_CHECKPOINT_DIR:null}
+      quantization:
+        type: ${env.QUANTIZATION_TYPE:bf16}
+      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:0}
+      max_batch_size: ${env.MAX_BATCH_SIZE:1}
+      max_seq_len: ${env.MAX_SEQ_LEN:4096}
   vector_io:
   - provider_id: faiss
     provider_type: inline::faiss

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

@@ -16,8 +16,12 @@ providers:
     provider_type: inline::meta-reference
     config:
       model: ${env.INFERENCE_MODEL}
-      max_seq_len: 4096
       checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
+      quantization:
+        type: ${env.QUANTIZATION_TYPE:bf16}
+      model_parallel_size: ${env.MODEL_PARALLEL_SIZE:0}
+      max_batch_size: ${env.MAX_BATCH_SIZE:1}
+      max_seq_len: ${env.MAX_SEQ_LEN:4096}
   - provider_id: sentence-transformers
     provider_type: inline::sentence-transformers
     config: {}

llama_stack/templates/meta-reference-quantized-gpu/doc_template.md

@@ -1,113 +0,0 @@
----
-orphan: true
----
-# Meta Reference Quantized Distribution
-
-```{toctree}
-:maxdepth: 2
-:hidden:
-
-self
-```
-
-The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations:
-
-{{ providers_table }}
-
-The only difference vs. the `meta-reference-gpu` distribution is that it has support for more efficient inference -- with fp8, int4 quantization, etc.
-
-Note that you need access to nvidia GPUs to run this distribution. This distribution is not compatible with CPU-only machines or machines with AMD GPUs.
-
-{% if run_config_env_vars %}
-### Environment Variables
-
-The following environment variables can be configured:
-
-{% for var, (default_value, description) in run_config_env_vars.items() %}
-- `{{ var }}`: {{ description }} (default: `{{ default_value }}`)
-{% endfor %}
-{% endif %}
-
-
-## Prerequisite: Downloading Models
-
-Please use `llama model list --downloaded` to check that you have llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](https://llama-stack.readthedocs.io/en/latest/references/llama_cli_reference/download_models.html) here to download the models. Run `llama model list` to see the available models to download, and `llama model download` to download the checkpoints.
-
-```
-$ llama model list --downloaded
-┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━┓
-┃ Model                                   ┃ Size     ┃ Modified Time       ┃
-┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━┩
-│ Llama3.2-1B-Instruct:int4-qlora-eo8     │ 1.53 GB  │ 2025-02-26 11:22:28 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama3.2-1B                             │ 2.31 GB  │ 2025-02-18 21:48:52 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Prompt-Guard-86M                        │ 0.02 GB  │ 2025-02-26 11:29:28 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama3.2-3B-Instruct:int4-spinquant-eo8 │ 3.69 GB  │ 2025-02-26 11:37:41 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama3.2-3B                             │ 5.99 GB  │ 2025-02-18 21:51:26 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama3.1-8B                             │ 14.97 GB │ 2025-02-16 10:36:37 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama3.2-1B-Instruct:int4-spinquant-eo8 │ 1.51 GB  │ 2025-02-26 11:35:02 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama-Guard-3-1B                        │ 2.80 GB  │ 2025-02-26 11:20:46 │
-├─────────────────────────────────────────┼──────────┼─────────────────────┤
-│ Llama-Guard-3-1B:int4                   │ 0.43 GB  │ 2025-02-26 11:33:33 │
-└─────────────────────────────────────────┴──────────┴─────────────────────┘
-```
-
-## Running the Distribution
-
-You can do this via Conda (build code) or Docker which has a pre-built image.
-
-### Via Docker
-
-This method allows you to get started quickly without having to build the distribution code.
-
-```bash
-LLAMA_STACK_PORT=8321
-docker run \
-  -it \
-  --pull always \
-  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-  -v ~/.llama:/root/.llama \
-  llamastack/distribution-{{ name }} \
-  --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
-```
-
-If you are using Llama Stack Safety / Shield APIs, use:
-
-```bash
-docker run \
-  -it \
-  --pull always \
-  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-  -v ~/.llama:/root/.llama \
-  llamastack/distribution-{{ name }} \
-  --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
-  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
-```
-
-### Via Conda
-
-Make sure you have done `uv pip install llama-stack` and have the Llama Stack CLI available.
-
-```bash
-llama stack build --template {{ name }} --image-type conda
-llama stack run distributions/{{ name }}/run.yaml \
-  --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
-```
-
-If you are using Llama Stack Safety / Shield APIs, use:
-
-```bash
-llama stack run distributions/{{ name }}/run-with-safety.yaml \
-  --port $LLAMA_STACK_PORT \
-  --env INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
-  --env SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
-```

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

@@ -1,115 +0,0 @@
-# Copyright (c) Meta Platforms, Inc. and affiliates.
-# All rights reserved.
-#
-# This source code is licensed under the terms described in the LICENSE file in
-# the root directory of this source tree.
-
-from pathlib import Path
-
-from llama_stack.apis.models.models import ModelType
-from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
-from llama_stack.providers.inline.inference.meta_reference import (
-    MetaReferenceQuantizedInferenceConfig,
-)
-from llama_stack.providers.inline.inference.sentence_transformers import (
-    SentenceTransformersInferenceConfig,
-)
-from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
-from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
-
-
-def get_distribution_template() -> DistributionTemplate:
-    providers = {
-        "inference": ["inline::meta-reference-quantized"],
-        "vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
-        "safety": ["inline::llama-guard"],
-        "agents": ["inline::meta-reference"],
-        "telemetry": ["inline::meta-reference"],
-        "eval": ["inline::meta-reference"],
-        "datasetio": ["remote::huggingface", "inline::localfs"],
-        "scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
-        "tool_runtime": [
-            "remote::brave-search",
-            "remote::tavily-search",
-            "inline::code-interpreter",
-            "inline::rag-runtime",
-            "remote::model-context-protocol",
-        ],
-    }
-    default_tool_groups = [
-        ToolGroupInput(
-            toolgroup_id="builtin::websearch",
-            provider_id="tavily-search",
-        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::rag",
-            provider_id="rag-runtime",
-        ),
-        ToolGroupInput(
-            toolgroup_id="builtin::code_interpreter",
-            provider_id="code-interpreter",
-        ),
-    ]
-    name = "meta-reference-quantized-gpu"
-    inference_provider = Provider(
-        provider_id="meta-reference-inference",
-        provider_type="inline::meta-reference-quantized",
-        config=MetaReferenceQuantizedInferenceConfig.sample_run_config(
-            model="${env.INFERENCE_MODEL}",
-            checkpoint_dir="${env.INFERENCE_CHECKPOINT_DIR:null}",
-        ),
-    )
-    embedding_provider = Provider(
-        provider_id="sentence-transformers",
-        provider_type="inline::sentence-transformers",
-        config=SentenceTransformersInferenceConfig.sample_run_config(),
-    )
-    vector_io_provider = Provider(
-        provider_id="faiss",
-        provider_type="inline::faiss",
-        config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
-    )
-
-    inference_model = ModelInput(
-        model_id="${env.INFERENCE_MODEL}",
-        provider_id="meta-reference-inference",
-    )
-    embedding_model = ModelInput(
-        model_id="all-MiniLM-L6-v2",
-        provider_id="sentence-transformers",
-        model_type=ModelType.embedding,
-        metadata={
-            "embedding_dimension": 384,
-        },
-    )
-    return DistributionTemplate(
-        name=name,
-        distro_type="self_hosted",
-        description="Use Meta Reference with fp8, int4 quantization for running LLM inference",
-        template_path=Path(__file__).parent / "doc_template.md",
-        providers=providers,
-        run_configs={
-            "run.yaml": RunConfigSettings(
-                provider_overrides={
-                    "inference": [inference_provider, embedding_provider],
-                    "vector_io": [vector_io_provider],
-                },
-                default_models=[inference_model, embedding_model],
-                default_tool_groups=default_tool_groups,
-            ),
-        },
-        run_config_env_vars={
-            "LLAMA_STACK_PORT": (
-                "8321",
-                "Port for the Llama Stack distribution server",
-            ),
-            "INFERENCE_MODEL": (
-                "meta-llama/Llama-3.2-3B-Instruct",
-                "Inference model loaded into the Meta Reference server",
-            ),
-            "INFERENCE_CHECKPOINT_DIR": (
-                "null",
-                "Directory containing the Meta Reference model checkpoint",
-            ),
-        },
-    )

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

@@ -1,134 +0,0 @@
-version: '2'
-image_name: meta-reference-quantized-gpu
-apis:
-- agents
-- datasetio
-- eval
-- inference
-- safety
-- scoring
-- telemetry
-- tool_runtime
-- vector_io
-providers:
-  inference:
-  - provider_id: meta-reference-inference
-    provider_type: inline::meta-reference-quantized
-    config:
-      model: ${env.INFERENCE_MODEL}
-      max_seq_len: 4096
-      checkpoint_dir: ${env.INFERENCE_CHECKPOINT_DIR:null}
-      quantization:
-        type: fp8
-  - provider_id: sentence-transformers
-    provider_type: inline::sentence-transformers
-    config: {}
-  vector_io:
-  - provider_id: faiss
-    provider_type: inline::faiss
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/faiss_store.db
-  safety:
-  - provider_id: llama-guard
-    provider_type: inline::llama-guard
-    config:
-      excluded_categories: []
-  agents:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      persistence_store:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/agents_store.db
-  telemetry:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      service_name: "${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:
-  - provider_id: meta-reference
-    provider_type: inline::meta-reference
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/meta_reference_eval.db
-  datasetio:
-  - provider_id: huggingface
-    provider_type: remote::huggingface
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/huggingface_datasetio.db
-  - provider_id: localfs
-    provider_type: inline::localfs
-    config:
-      kvstore:
-        type: sqlite
-        namespace: null
-        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/localfs_datasetio.db
-  scoring:
-  - provider_id: basic
-    provider_type: inline::basic
-    config: {}
-  - provider_id: llm-as-judge
-    provider_type: inline::llm-as-judge
-    config: {}
-  - provider_id: braintrust
-    provider_type: inline::braintrust
-    config:
-      openai_api_key: ${env.OPENAI_API_KEY:}
-  tool_runtime:
-  - provider_id: brave-search
-    provider_type: remote::brave-search
-    config:
-      api_key: ${env.BRAVE_SEARCH_API_KEY:}
-      max_results: 3
-  - provider_id: tavily-search
-    provider_type: remote::tavily-search
-    config:
-      api_key: ${env.TAVILY_SEARCH_API_KEY:}
-      max_results: 3
-  - provider_id: code-interpreter
-    provider_type: inline::code-interpreter
-    config: {}
-  - provider_id: rag-runtime
-    provider_type: inline::rag-runtime
-    config: {}
-  - provider_id: model-context-protocol
-    provider_type: remote::model-context-protocol
-    config: {}
-metadata_store:
-  type: sqlite
-  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/meta-reference-quantized-gpu}/registry.db
-models:
-- metadata: {}
-  model_id: ${env.INFERENCE_MODEL}
-  provider_id: meta-reference-inference
-  model_type: llm
-- metadata:
-    embedding_dimension: 384
-  model_id: all-MiniLM-L6-v2
-  provider_id: sentence-transformers
-  model_type: embedding
-shields: []
-vector_dbs: []
-datasets: []
-scoring_fns: []
-benchmarks: []
-tool_groups:
-- toolgroup_id: builtin::websearch
-  provider_id: tavily-search
-- toolgroup_id: builtin::rag
-  provider_id: rag-runtime
-- toolgroup_id: builtin::code_interpreter
-  provider_id: code-interpreter
-server:
-  port: 8321

llama_stack/templates/remote-vllm/doc_template.md

@@ -13,7 +13,7 @@ The `llamastack/distribution-{{ name }}` distribution consists of the following
 
 {{ providers_table }}
 
-You can use this distribution if you have GPUs and want to run an independent vLLM server container for running inference.
+You can use this distribution if you want to run an independent vLLM server for inference.
 
 {% if run_config_env_vars %}
 ### Environment Variables
@@ -28,6 +28,83 @@ The following environment variables can be configured:
 
 ## Setting up vLLM server
 
+In the following sections, we'll use either AMD and NVIDIA GPUs to serve as hardware accelerators for the vLLM
+server, which acts as both the LLM inference provider and the safety provider. Note that vLLM also
+[supports many other hardware accelerators](https://docs.vllm.ai/en/latest/getting_started/installation.html) and
+that we only use GPUs here for demonstration purposes.
+
+### Setting up vLLM server on AMD GPU
+
+AMD provides two main vLLM container options:
+- rocm/vllm: Production-ready container
+- rocm/vllm-dev: Development container with the latest vLLM features
+
+Please check the [Blog about ROCm vLLM Usage](https://rocm.blogs.amd.com/software-tools-optimization/vllm-container/README.html) to get more details.
+
+Here is a sample script to start a ROCm vLLM server locally via Docker:
+
+```bash
+export INFERENCE_PORT=8000
+export INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct
+export CUDA_VISIBLE_DEVICES=0
+export VLLM_DIMG="rocm/vllm-dev:main"
+
+docker run \
+    --pull always \
+    --ipc=host \
+    --privileged \
+    --shm-size 16g \
+    --device=/dev/kfd \
+    --device=/dev/dri \
+    --group-add video \
+    --cap-add=SYS_PTRACE \
+    --cap-add=CAP_SYS_ADMIN \
+    --security-opt seccomp=unconfined \
+    --security-opt apparmor=unconfined \
+    --env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \
+    --env "HIP_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES" \
+    -p $INFERENCE_PORT:$INFERENCE_PORT \
+    -v ~/.cache/huggingface:/root/.cache/huggingface \
+    $VLLM_DIMG \
+    python -m vllm.entrypoints.openai.api_server \
+    --model $INFERENCE_MODEL \
+    --port $INFERENCE_PORT
+```
+
+Note that you'll also need to set `--enable-auto-tool-choice` and `--tool-call-parser` to [enable tool calling in vLLM](https://docs.vllm.ai/en/latest/features/tool_calling.html).
+
+If you are using Llama Stack Safety / Shield APIs, then you will need to also run another instance of a vLLM with a corresponding safety model like `meta-llama/Llama-Guard-3-1B` using a script like:
+
+```bash
+export SAFETY_PORT=8081
+export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
+export CUDA_VISIBLE_DEVICES=1
+export VLLM_DIMG="rocm/vllm-dev:main"
+
+docker run \
+    --pull always \
+    --ipc=host \
+    --privileged \
+    --shm-size 16g \
+    --device=/dev/kfd \
+    --device=/dev/dri \
+    --group-add video \
+    --cap-add=SYS_PTRACE \
+    --cap-add=CAP_SYS_ADMIN \
+    --security-opt seccomp=unconfined \
+    --security-opt apparmor=unconfined \
+    --env "HUGGING_FACE_HUB_TOKEN=$HF_TOKEN" \
+    --env "HIP_VISIBLE_DEVICES=$CUDA_VISIBLE_DEVICES" \
+    -p $SAFETY_PORT:$SAFETY_PORT \
+    -v ~/.cache/huggingface:/root/.cache/huggingface \
+    $VLLM_DIMG \
+    python -m vllm.entrypoints.openai.api_server \
+    --model $SAFETY_MODEL \
+    --port $SAFETY_PORT
+```
+
+### Setting up vLLM server on NVIDIA GPU
+
 Please check the [vLLM Documentation](https://docs.vllm.ai/en/v0.5.5/serving/deploying_with_docker.html) to get a vLLM endpoint. Here is a sample script to start a vLLM server locally via Docker:
 
 ```bash

llama_stack/templates/sambanova/run.yaml

@@ -165,6 +165,16 @@ models:
   provider_id: sambanova
   provider_model_id: Meta-Llama-Guard-3-8B
   model_type: llm
+- metadata: {}
+  model_id: Llama-4-Scout-17B-16E-Instruct
+  provider_id: sambanova
+  provider_model_id: Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: sambanova
+  provider_model_id: Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
 shields:
 - shield_id: meta-llama/Llama-Guard-3-8B
 vector_dbs: []

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

@@ -219,6 +219,36 @@ models:
   provider_id: together
   provider_model_id: togethercomputer/m2-bert-80M-32k-retrieval
   model_type: embedding
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2

llama_stack/templates/together/run.yaml

@@ -214,6 +214,36 @@ models:
   provider_id: together
   provider_model_id: togethercomputer/m2-bert-80M-32k-retrieval
   model_type: embedding
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  provider_id: together
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
 - metadata:
     embedding_dimension: 384
   model_id: all-MiniLM-L6-v2

llama_stack/templates/verification/__init__.py

@@ -4,4 +4,4 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from .meta_reference import get_distribution_template  # noqa: F401
+from .verification import get_distribution_template  # noqa: F401

llama_stack/templates/verification/build.yaml

@@ -1,11 +1,17 @@
 version: '2'
 distribution_spec:
-  description: Use Meta Reference with fp8, int4 quantization for running LLM inference
+  description: Distribution for running e2e tests in CI
   providers:
     inference:
-    - inline::meta-reference-quantized
+    - remote::openai
+    - remote::fireworks-openai-compat
+    - remote::together-openai-compat
+    - remote::groq-openai-compat
+    - remote::sambanova-openai-compat
+    - remote::cerebras-openai-compat
+    - inline::sentence-transformers
     vector_io:
-    - inline::faiss
+    - inline::sqlite-vec
     - remote::chromadb
     - remote::pgvector
     safety:

llama_stack/templates/verification/run.yaml

@@ -0,0 +1,646 @@
+version: '2'
+image_name: verification
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- safety
+- scoring
+- telemetry
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: openai
+    provider_type: remote::openai
+    config:
+      api_key: ${env.OPENAI_API_KEY:}
+  - provider_id: fireworks-openai-compat
+    provider_type: remote::fireworks-openai-compat
+    config:
+      openai_compat_api_base: https://api.fireworks.ai/inference/v1
+      api_key: ${env.FIREWORKS_API_KEY:}
+  - provider_id: together-openai-compat
+    provider_type: remote::together-openai-compat
+    config:
+      openai_compat_api_base: https://api.together.xyz/v1
+      api_key: ${env.TOGETHER_API_KEY:}
+  - provider_id: groq-openai-compat
+    provider_type: remote::groq-openai-compat
+    config:
+      openai_compat_api_base: https://api.groq.com/openai/v1
+      api_key: ${env.GROQ_API_KEY:}
+  - provider_id: sambanova-openai-compat
+    provider_type: remote::sambanova-openai-compat
+    config:
+      openai_compat_api_base: https://api.sambanova.ai/v1
+      api_key: ${env.SAMBANOVA_API_KEY:}
+  - provider_id: cerebras-openai-compat
+    provider_type: remote::cerebras-openai-compat
+    config:
+      openai_compat_api_base: https://api.cerebras.ai/v1
+      api_key: ${env.CEREBRAS_API_KEY:}
+  - provider_id: sentence-transformers
+    provider_type: inline::sentence-transformers
+    config: {}
+  vector_io:
+  - provider_id: sqlite-vec
+    provider_type: inline::sqlite-vec
+    config:
+      db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/sqlite_vec.db
+  - provider_id: ${env.ENABLE_CHROMADB+chromadb}
+    provider_type: remote::chromadb
+    config:
+      url: ${env.CHROMADB_URL:}
+  - provider_id: ${env.ENABLE_PGVECTOR+pgvector}
+    provider_type: remote::pgvector
+    config:
+      host: ${env.PGVECTOR_HOST:localhost}
+      port: ${env.PGVECTOR_PORT:5432}
+      db: ${env.PGVECTOR_DB:}
+      user: ${env.PGVECTOR_USER:}
+      password: ${env.PGVECTOR_PASSWORD:}
+  safety:
+  - provider_id: llama-guard
+    provider_type: inline::llama-guard
+    config:
+      excluded_categories: []
+  agents:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      persistence_store:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/agents_store.db
+  telemetry:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      service_name: "${env.OTEL_SERVICE_NAME:\u200B}"
+      sinks: ${env.TELEMETRY_SINKS:console,sqlite}
+      sqlite_db_path: ${env.SQLITE_DB_PATH:~/.llama/distributions/verification/trace_store.db}
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/meta_reference_eval.db
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/huggingface_datasetio.db
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        type: sqlite
+        namespace: null
+        db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/localfs_datasetio.db
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+    config: {}
+  - provider_id: llm-as-judge
+    provider_type: inline::llm-as-judge
+    config: {}
+  - provider_id: braintrust
+    provider_type: inline::braintrust
+    config:
+      openai_api_key: ${env.OPENAI_API_KEY:}
+  tool_runtime:
+  - provider_id: brave-search
+    provider_type: remote::brave-search
+    config:
+      api_key: ${env.BRAVE_SEARCH_API_KEY:}
+      max_results: 3
+  - provider_id: tavily-search
+    provider_type: remote::tavily-search
+    config:
+      api_key: ${env.TAVILY_SEARCH_API_KEY:}
+      max_results: 3
+  - provider_id: code-interpreter
+    provider_type: inline::code-interpreter
+    config: {}
+  - provider_id: rag-runtime
+    provider_type: inline::rag-runtime
+    config: {}
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+    config: {}
+metadata_store:
+  type: sqlite
+  db_path: ${env.SQLITE_STORE_DIR:~/.llama/distributions/verification}/registry.db
+models:
+- metadata: {}
+  model_id: openai/gpt-4o
+  provider_id: openai
+  provider_model_id: openai/gpt-4o
+  model_type: llm
+- metadata: {}
+  model_id: openai/gpt-4o-mini
+  provider_id: openai
+  provider_model_id: openai/gpt-4o-mini
+  model_type: llm
+- metadata: {}
+  model_id: openai/chatgpt-4o-latest
+  provider_id: openai
+  provider_model_id: openai/chatgpt-4o-latest
+  model_type: llm
+- metadata:
+    embedding_dimension: 1536
+    context_length: 8192
+  model_id: openai/text-embedding-3-small
+  provider_id: openai
+  provider_model_id: openai/text-embedding-3-small
+  model_type: embedding
+- metadata:
+    embedding_dimension: 3072
+    context_length: 8192
+  model_id: openai/text-embedding-3-large
+  provider_id: openai
+  provider_model_id: openai/text-embedding-3-large
+  model_type: embedding
+- metadata: {}
+  model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-8B-Instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p1-8b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-70B-Instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p1-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p1-405b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-3B-Instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p2-3b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-v3p3-70b-instruct
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama-guard-3-8b
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-guard-3-8b
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-Guard-3-8B
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-guard-3-8b
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama-guard-3-11b-vision
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-Guard-3-11B-Vision
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama-guard-3-11b-vision
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama4-scout-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: fireworks-openai-compat
+  provider_model_id: accounts/fireworks/models/llama4-maverick-instruct-basic
+  model_type: llm
+- metadata:
+    embedding_dimension: 768
+    context_length: 8192
+  model_id: nomic-ai/nomic-embed-text-v1.5
+  provider_id: fireworks-openai-compat
+  provider_model_id: nomic-ai/nomic-embed-text-v1.5
+  model_type: embedding
+- metadata: {}
+  model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-8B-Instruct
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-70B-Instruct
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-3B-Instruct
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-3.2-3B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-3.2-11B-Vision-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-3.2-90B-Vision-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-3.3-70B-Instruct-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Meta-Llama-Guard-3-8B
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-Guard-3-8B
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Meta-Llama-Guard-3-8B
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-Guard-3-11B-Vision
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-Guard-3-11B-Vision-Turbo
+  model_type: llm
+- metadata:
+    embedding_dimension: 768
+    context_length: 8192
+  model_id: togethercomputer/m2-bert-80M-8k-retrieval
+  provider_id: together-openai-compat
+  provider_model_id: togethercomputer/m2-bert-80M-8k-retrieval
+  model_type: embedding
+- metadata:
+    embedding_dimension: 768
+    context_length: 32768
+  model_id: togethercomputer/m2-bert-80M-32k-retrieval
+  provider_id: together-openai-compat
+  provider_model_id: togethercomputer/m2-bert-80M-32k-retrieval
+  model_type: embedding
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
+- metadata: {}
+  model_id: together/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  provider_id: together-openai-compat
+  provider_model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8
+  model_type: llm
+- metadata: {}
+  model_id: groq/llama3-8b-8192
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama3-8b-8192
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-8B-Instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama3-8b-8192
+  model_type: llm
+- metadata: {}
+  model_id: groq/llama-3.1-8b-instant
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama-3.1-8b-instant
+  model_type: llm
+- metadata: {}
+  model_id: groq/llama3-70b-8192
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama3-70b-8192
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3-70B-Instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama3-70b-8192
+  model_type: llm
+- metadata: {}
+  model_id: groq/llama-3.3-70b-versatile
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama-3.3-70b-versatile
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama-3.3-70b-versatile
+  model_type: llm
+- metadata: {}
+  model_id: groq/llama-3.2-3b-preview
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama-3.2-3b-preview
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-3B-Instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama-3.2-3b-preview
+  model_type: llm
+- metadata: {}
+  model_id: groq/llama-4-scout-17b-16e-instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/meta-llama/llama-4-scout-17b-16e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: groq/llama-4-maverick-17b-128e-instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/llama-4-maverick-17b-128e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Maverick-17B-128E-Instruct
+  provider_id: groq-openai-compat
+  provider_model_id: groq/meta-llama/llama-4-maverick-17b-128e-instruct
+  model_type: llm
+- metadata: {}
+  model_id: Meta-Llama-3.1-8B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.1-8B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-8B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.1-8B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: Meta-Llama-3.1-70B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.1-70B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-70B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.1-70B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: Meta-Llama-3.1-405B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.1-405B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-405B-Instruct-FP8
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.1-405B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: Meta-Llama-3.2-1B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.2-1B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-1B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.2-1B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: Meta-Llama-3.2-3B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.2-3B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-3B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.2-3B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: Meta-Llama-3.3-70B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.3-70B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-3.3-70B-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: Llama-3.2-11B-Vision-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Llama-3.2-11B-Vision-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-11B-Vision-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Llama-3.2-11B-Vision-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: Llama-3.2-90B-Vision-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Llama-3.2-90B-Vision-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.2-90B-Vision-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Llama-3.2-90B-Vision-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: Meta-Llama-Guard-3-8B
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-Guard-3-8B
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-Guard-3-8B
+  provider_id: sambanova-openai-compat
+  provider_model_id: Meta-Llama-Guard-3-8B
+  model_type: llm
+- metadata: {}
+  model_id: Llama-4-Scout-17B-16E-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-4-Scout-17B-16E-Instruct
+  provider_id: sambanova-openai-compat
+  provider_model_id: Llama-4-Scout-17B-16E-Instruct
+  model_type: llm
+- metadata: {}
+  model_id: llama3.1-8b
+  provider_id: cerebras-openai-compat
+  provider_model_id: llama3.1-8b
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.1-8B-Instruct
+  provider_id: cerebras-openai-compat
+  provider_model_id: llama3.1-8b
+  model_type: llm
+- metadata: {}
+  model_id: llama-3.3-70b
+  provider_id: cerebras-openai-compat
+  provider_model_id: llama-3.3-70b
+  model_type: llm
+- metadata: {}
+  model_id: meta-llama/Llama-3.3-70B-Instruct
+  provider_id: cerebras-openai-compat
+  provider_model_id: llama-3.3-70b
+  model_type: llm
+- metadata:
+    embedding_dimension: 384
+  model_id: all-MiniLM-L6-v2
+  provider_id: sentence-transformers
+  model_type: embedding
+shields:
+- shield_id: meta-llama/Llama-Guard-3-8B
+vector_dbs: []
+datasets: []
+scoring_fns: []
+benchmarks: []
+tool_groups:
+- toolgroup_id: builtin::websearch
+  provider_id: tavily-search
+- toolgroup_id: builtin::rag
+  provider_id: rag-runtime
+- toolgroup_id: builtin::code_interpreter
+  provider_id: code-interpreter
+server:
+  port: 8321

llama_stack/templates/verification/verification.py

@@ -0,0 +1,207 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+from typing import Dict, List, Tuple
+
+from llama_stack.apis.models.models import ModelType
+from llama_stack.distribution.datatypes import (
+    ModelInput,
+    Provider,
+    ShieldInput,
+    ToolGroupInput,
+)
+from llama_stack.providers.inline.inference.sentence_transformers import (
+    SentenceTransformersInferenceConfig,
+)
+from llama_stack.providers.inline.vector_io.sqlite_vec.config import (
+    SQLiteVectorIOConfig,
+)
+from llama_stack.providers.remote.inference.cerebras.models import MODEL_ENTRIES as CEREBRAS_MODEL_ENTRIES
+from llama_stack.providers.remote.inference.cerebras_openai_compat.config import CerebrasCompatConfig
+from llama_stack.providers.remote.inference.fireworks.models import (
+    MODEL_ENTRIES as FIREWORKS_MODEL_ENTRIES,
+)
+from llama_stack.providers.remote.inference.fireworks_openai_compat.config import FireworksCompatConfig
+from llama_stack.providers.remote.inference.groq.models import (
+    MODEL_ENTRIES as GROQ_MODEL_ENTRIES,
+)
+from llama_stack.providers.remote.inference.groq_openai_compat.config import GroqCompatConfig
+from llama_stack.providers.remote.inference.openai.config import OpenAIConfig
+from llama_stack.providers.remote.inference.openai.models import (
+    MODEL_ENTRIES as OPENAI_MODEL_ENTRIES,
+)
+from llama_stack.providers.remote.inference.sambanova.models import MODEL_ENTRIES as SAMBANOVA_MODEL_ENTRIES
+from llama_stack.providers.remote.inference.sambanova_openai_compat.config import SambaNovaCompatConfig
+from llama_stack.providers.remote.inference.together.models import (
+    MODEL_ENTRIES as TOGETHER_MODEL_ENTRIES,
+)
+from llama_stack.providers.remote.inference.together_openai_compat.config import TogetherCompatConfig
+from llama_stack.providers.remote.vector_io.chroma.config import ChromaVectorIOConfig
+from llama_stack.providers.remote.vector_io.pgvector.config import (
+    PGVectorVectorIOConfig,
+)
+from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry
+from llama_stack.templates.template import (
+    DistributionTemplate,
+    RunConfigSettings,
+    get_model_registry,
+)
+
+
+def get_inference_providers() -> Tuple[List[Provider], Dict[str, List[ProviderModelEntry]]]:
+    # in this template, we allow each API key to be optional
+    providers = [
+        (
+            "openai",
+            OPENAI_MODEL_ENTRIES,
+            OpenAIConfig.sample_run_config(api_key="${env.OPENAI_API_KEY:}"),
+        ),
+        (
+            "fireworks-openai-compat",
+            FIREWORKS_MODEL_ENTRIES,
+            FireworksCompatConfig.sample_run_config(api_key="${env.FIREWORKS_API_KEY:}"),
+        ),
+        (
+            "together-openai-compat",
+            TOGETHER_MODEL_ENTRIES,
+            TogetherCompatConfig.sample_run_config(api_key="${env.TOGETHER_API_KEY:}"),
+        ),
+        (
+            "groq-openai-compat",
+            GROQ_MODEL_ENTRIES,
+            GroqCompatConfig.sample_run_config(api_key="${env.GROQ_API_KEY:}"),
+        ),
+        (
+            "sambanova-openai-compat",
+            SAMBANOVA_MODEL_ENTRIES,
+            SambaNovaCompatConfig.sample_run_config(api_key="${env.SAMBANOVA_API_KEY:}"),
+        ),
+        (
+            "cerebras-openai-compat",
+            CEREBRAS_MODEL_ENTRIES,
+            CerebrasCompatConfig.sample_run_config(api_key="${env.CEREBRAS_API_KEY:}"),
+        ),
+    ]
+    inference_providers = []
+    available_models = {}
+    for provider_id, model_entries, config in providers:
+        inference_providers.append(
+            Provider(
+                provider_id=provider_id,
+                provider_type=f"remote::{provider_id}",
+                config=config,
+            )
+        )
+        available_models[provider_id] = model_entries
+    return inference_providers, available_models
+
+
+def get_distribution_template() -> DistributionTemplate:
+    inference_providers, available_models = get_inference_providers()
+    providers = {
+        "inference": ([p.provider_type for p in inference_providers] + ["inline::sentence-transformers"]),
+        "vector_io": ["inline::sqlite-vec", "remote::chromadb", "remote::pgvector"],
+        "safety": ["inline::llama-guard"],
+        "agents": ["inline::meta-reference"],
+        "telemetry": ["inline::meta-reference"],
+        "eval": ["inline::meta-reference"],
+        "datasetio": ["remote::huggingface", "inline::localfs"],
+        "scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
+        "tool_runtime": [
+            "remote::brave-search",
+            "remote::tavily-search",
+            "inline::code-interpreter",
+            "inline::rag-runtime",
+            "remote::model-context-protocol",
+        ],
+    }
+    name = "verification"
+
+    vector_io_providers = [
+        Provider(
+            provider_id="sqlite-vec",
+            provider_type="inline::sqlite-vec",
+            config=SQLiteVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
+        ),
+        Provider(
+            provider_id="${env.ENABLE_CHROMADB+chromadb}",
+            provider_type="remote::chromadb",
+            config=ChromaVectorIOConfig.sample_run_config(url="${env.CHROMADB_URL:}"),
+        ),
+        Provider(
+            provider_id="${env.ENABLE_PGVECTOR+pgvector}",
+            provider_type="remote::pgvector",
+            config=PGVectorVectorIOConfig.sample_run_config(
+                db="${env.PGVECTOR_DB:}",
+                user="${env.PGVECTOR_USER:}",
+                password="${env.PGVECTOR_PASSWORD:}",
+            ),
+        ),
+    ]
+    embedding_provider = Provider(
+        provider_id="sentence-transformers",
+        provider_type="inline::sentence-transformers",
+        config=SentenceTransformersInferenceConfig.sample_run_config(),
+    )
+
+    default_tool_groups = [
+        ToolGroupInput(
+            toolgroup_id="builtin::websearch",
+            provider_id="tavily-search",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::rag",
+            provider_id="rag-runtime",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::code_interpreter",
+            provider_id="code-interpreter",
+        ),
+    ]
+    embedding_model = ModelInput(
+        model_id="all-MiniLM-L6-v2",
+        provider_id=embedding_provider.provider_id,
+        model_type=ModelType.embedding,
+        metadata={
+            "embedding_dimension": 384,
+        },
+    )
+
+    default_models = get_model_registry(available_models)
+    return DistributionTemplate(
+        name=name,
+        distro_type="self_hosted",
+        description="Distribution for running e2e tests in CI",
+        container_image=None,
+        template_path=None,
+        providers=providers,
+        available_models_by_provider=available_models,
+        run_configs={
+            "run.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": inference_providers + [embedding_provider],
+                    "vector_io": vector_io_providers,
+                },
+                default_models=default_models + [embedding_model],
+                default_tool_groups=default_tool_groups,
+                default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
+            ),
+        },
+        run_config_env_vars={
+            "LLAMA_STACK_PORT": (
+                "8321",
+                "Port for the Llama Stack distribution server",
+            ),
+            "FIREWORKS_API_KEY": (
+                "",
+                "Fireworks API Key",
+            ),
+            "OPENAI_API_KEY": (
+                "",
+                "OpenAI API Key",
+            ),
+        },
+    )