chore(package): migrate to src/ layout (#3920)

Migrates package structure to src/ layout following Python packaging
best practices.

All code moved from `llama_stack/` to `src/llama_stack/`. Public API
unchanged - imports remain `import llama_stack.*`.

Updated build configs, pre-commit hooks, scripts, and GitHub workflows
accordingly. All hooks pass, package builds cleanly.

**Developer note**: Reinstall after pulling: `pip install -e .`

src/llama_stack/distributions/meta-reference-gpu/__init__.py

@@ -0,0 +1,7 @@
+# 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 .meta_reference import get_distribution_template  # noqa: F401

src/llama_stack/distributions/meta-reference-gpu/build.yaml

@@ -0,0 +1,32 @@
+version: 2
+distribution_spec:
+  description: Use Meta Reference for running LLM inference
+  providers:
+    inference:
+    - provider_type: inline::meta-reference
+    vector_io:
+    - provider_type: inline::faiss
+    - provider_type: remote::chromadb
+    - provider_type: remote::pgvector
+    safety:
+    - provider_type: inline::llama-guard
+    agents:
+    - provider_type: inline::meta-reference
+    eval:
+    - provider_type: inline::meta-reference
+    datasetio:
+    - provider_type: remote::huggingface
+    - provider_type: inline::localfs
+    scoring:
+    - provider_type: inline::basic
+    - provider_type: inline::llm-as-judge
+    - provider_type: inline::braintrust
+    tool_runtime:
+    - provider_type: remote::brave-search
+    - provider_type: remote::tavily-search
+    - provider_type: inline::rag-runtime
+    - provider_type: remote::model-context-protocol
+image_type: venv
+additional_pip_packages:
+- aiosqlite
+- sqlalchemy[asyncio]

src/llama_stack/distributions/meta-reference-gpu/doc_template.md

@@ -0,0 +1,89 @@
+---
+orphan: true
+---
+# Meta Reference GPU Distribution
+
+```{toctree}
+:maxdepth: 2
+:hidden:
+
+self
+```
+
+The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations:
+
+{{ providers_table }}
+
+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 check that you have llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](../../references/llama_cli_reference/download_models.md) here to download the models using the Hugging Face CLI.
+```
+
+## Running the Distribution
+
+You can do this via venv 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 \
+  --gpu all \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ~/.llama:/root/.llama \
+  -e INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  llamastack/distribution-{{ name }} \
+  --port $LLAMA_STACK_PORT
+```
+
+If you are using Llama Stack Safety / Shield APIs, use:
+
+```bash
+docker run \
+  -it \
+  --pull always \
+  --gpu all \
+  -p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
+  -v ~/.llama:/root/.llama \
+  -e INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+  -e SAFETY_MODEL=meta-llama/Llama-Guard-3-1B \
+  llamastack/distribution-{{ name }} \
+  --port $LLAMA_STACK_PORT
+```
+
+### Via venv
+
+Make sure you have the Llama Stack CLI available.
+
+```bash
+llama stack list-deps meta-reference-gpu | xargs -L1 uv pip install
+INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+llama stack run distributions/{{ name }}/run.yaml \
+  --port 8321
+```
+
+If you are using Llama Stack Safety / Shield APIs, use:
+
+```bash
+INFERENCE_MODEL=meta-llama/Llama-3.2-3B-Instruct \
+SAFETY_MODEL=meta-llama/Llama-Guard-3-1B \
+llama stack run distributions/{{ name }}/run-with-safety.yaml \
+  --port 8321
+```

src/llama_stack/distributions/meta-reference-gpu/meta_reference.py

@@ -0,0 +1,163 @@
+# 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 import ModelType
+from llama_stack.core.datatypes import (
+    BuildProvider,
+    ModelInput,
+    Provider,
+    ShieldInput,
+    ToolGroupInput,
+)
+from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings
+from llama_stack.providers.inline.inference.meta_reference import (
+    MetaReferenceInferenceConfig,
+)
+from llama_stack.providers.inline.inference.sentence_transformers import (
+    SentenceTransformersInferenceConfig,
+)
+from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
+
+
+def get_distribution_template() -> DistributionTemplate:
+    providers = {
+        "inference": [BuildProvider(provider_type="inline::meta-reference")],
+        "vector_io": [
+            BuildProvider(provider_type="inline::faiss"),
+            BuildProvider(provider_type="remote::chromadb"),
+            BuildProvider(provider_type="remote::pgvector"),
+        ],
+        "safety": [BuildProvider(provider_type="inline::llama-guard")],
+        "agents": [BuildProvider(provider_type="inline::meta-reference")],
+        "eval": [BuildProvider(provider_type="inline::meta-reference")],
+        "datasetio": [
+            BuildProvider(provider_type="remote::huggingface"),
+            BuildProvider(provider_type="inline::localfs"),
+        ],
+        "scoring": [
+            BuildProvider(provider_type="inline::basic"),
+            BuildProvider(provider_type="inline::llm-as-judge"),
+            BuildProvider(provider_type="inline::braintrust"),
+        ],
+        "tool_runtime": [
+            BuildProvider(provider_type="remote::brave-search"),
+            BuildProvider(provider_type="remote::tavily-search"),
+            BuildProvider(provider_type="inline::rag-runtime"),
+            BuildProvider(provider_type="remote::model-context-protocol"),
+        ],
+    }
+    name = "meta-reference-gpu"
+    inference_provider = Provider(
+        provider_id="meta-reference-inference",
+        provider_type="inline::meta-reference",
+        config=MetaReferenceInferenceConfig.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="${env.INFERENCE_MODEL}",
+        provider_id="meta-reference-inference",
+    )
+    embedding_model = ModelInput(
+        model_id="nomic-embed-text-v1.5",
+        provider_id="sentence-transformers",
+        model_type=ModelType.embedding,
+        metadata={
+            "embedding_dimension": 768,
+        },
+    )
+    safety_model = ModelInput(
+        model_id="${env.SAFETY_MODEL}",
+        provider_id="meta-reference-safety",
+    )
+    default_tool_groups = [
+        ToolGroupInput(
+            toolgroup_id="builtin::websearch",
+            provider_id="tavily-search",
+        ),
+        ToolGroupInput(
+            toolgroup_id="builtin::rag",
+            provider_id="rag-runtime",
+        ),
+    ]
+
+    return DistributionTemplate(
+        name=name,
+        distro_type="self_hosted",
+        description="Use Meta Reference 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-with-safety.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [
+                        inference_provider,
+                        embedding_provider,
+                        Provider(
+                            provider_id="meta-reference-safety",
+                            provider_type="inline::meta-reference",
+                            config=MetaReferenceInferenceConfig.sample_run_config(
+                                model="${env.SAFETY_MODEL}",
+                                checkpoint_dir="${env.SAFETY_CHECKPOINT_DIR:=null}",
+                            ),
+                        ),
+                    ],
+                    "vector_io": [vector_io_provider],
+                },
+                default_models=[
+                    inference_model,
+                    safety_model,
+                    embedding_model,
+                ],
+                default_shields=[ShieldInput(shield_id="${env.SAFETY_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",
+            ),
+            "SAFETY_MODEL": (
+                "meta-llama/Llama-Guard-3-1B",
+                "Name of the safety (Llama-Guard) model to use",
+            ),
+            "SAFETY_CHECKPOINT_DIR": (
+                "null",
+                "Directory containing the Llama-Guard model checkpoint",
+            ),
+        },
+    )

src/llama_stack/distributions/meta-reference-gpu/run-with-safety.yaml

@@ -0,0 +1,154 @@
+version: 2
+image_name: meta-reference-gpu
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- safety
+- scoring
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: meta-reference-inference
+    provider_type: inline::meta-reference
+    config:
+      model: ${env.INFERENCE_MODEL}
+      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
+  - provider_id: meta-reference-safety
+    provider_type: inline::meta-reference
+    config:
+      model: ${env.SAFETY_MODEL}
+      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
+    config:
+      persistence:
+        namespace: vector_io::faiss
+        backend: kv_default
+  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:
+        agent_state:
+          namespace: agents
+          backend: kv_default
+        responses:
+          table_name: responses
+          backend: sql_default
+          max_write_queue_size: 10000
+          num_writers: 4
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        namespace: eval
+        backend: kv_default
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        namespace: datasetio::huggingface
+        backend: kv_default
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        namespace: datasetio::localfs
+        backend: kv_default
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+  - provider_id: llm-as-judge
+    provider_type: inline::llm-as-judge
+  - 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: rag-runtime
+    provider_type: inline::rag-runtime
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+storage:
+  backends:
+    kv_default:
+      type: kv_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/kvstore.db
+    sql_default:
+      type: sql_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/sql_store.db
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
+registered_resources:
+  models:
+  - metadata: {}
+    model_id: ${env.INFERENCE_MODEL}
+    provider_id: meta-reference-inference
+    model_type: llm
+  - metadata: {}
+    model_id: ${env.SAFETY_MODEL}
+    provider_id: meta-reference-safety
+    model_type: llm
+  - metadata:
+      embedding_dimension: 768
+    model_id: nomic-embed-text-v1.5
+    provider_id: sentence-transformers
+    model_type: embedding
+  shields:
+  - shield_id: ${env.SAFETY_MODEL}
+  vector_dbs: []
+  datasets: []
+  scoring_fns: []
+  benchmarks: []
+  tool_groups:
+  - toolgroup_id: builtin::websearch
+    provider_id: tavily-search
+  - toolgroup_id: builtin::rag
+    provider_id: rag-runtime
+server:
+  port: 8321
+telemetry:
+  enabled: true

src/llama_stack/distributions/meta-reference-gpu/run.yaml

@@ -0,0 +1,142 @@
+version: 2
+image_name: meta-reference-gpu
+apis:
+- agents
+- datasetio
+- eval
+- inference
+- safety
+- scoring
+- tool_runtime
+- vector_io
+providers:
+  inference:
+  - provider_id: meta-reference-inference
+    provider_type: inline::meta-reference
+    config:
+      model: ${env.INFERENCE_MODEL}
+      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
+  vector_io:
+  - provider_id: faiss
+    provider_type: inline::faiss
+    config:
+      persistence:
+        namespace: vector_io::faiss
+        backend: kv_default
+  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:
+        agent_state:
+          namespace: agents
+          backend: kv_default
+        responses:
+          table_name: responses
+          backend: sql_default
+          max_write_queue_size: 10000
+          num_writers: 4
+  eval:
+  - provider_id: meta-reference
+    provider_type: inline::meta-reference
+    config:
+      kvstore:
+        namespace: eval
+        backend: kv_default
+  datasetio:
+  - provider_id: huggingface
+    provider_type: remote::huggingface
+    config:
+      kvstore:
+        namespace: datasetio::huggingface
+        backend: kv_default
+  - provider_id: localfs
+    provider_type: inline::localfs
+    config:
+      kvstore:
+        namespace: datasetio::localfs
+        backend: kv_default
+  scoring:
+  - provider_id: basic
+    provider_type: inline::basic
+  - provider_id: llm-as-judge
+    provider_type: inline::llm-as-judge
+  - 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: rag-runtime
+    provider_type: inline::rag-runtime
+  - provider_id: model-context-protocol
+    provider_type: remote::model-context-protocol
+storage:
+  backends:
+    kv_default:
+      type: kv_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/kvstore.db
+    sql_default:
+      type: sql_sqlite
+      db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/meta-reference-gpu}/sql_store.db
+  stores:
+    metadata:
+      namespace: registry
+      backend: kv_default
+    inference:
+      table_name: inference_store
+      backend: sql_default
+      max_write_queue_size: 10000
+      num_writers: 4
+    conversations:
+      table_name: openai_conversations
+      backend: sql_default
+    prompts:
+      namespace: prompts
+      backend: kv_default
+registered_resources:
+  models:
+  - metadata: {}
+    model_id: ${env.INFERENCE_MODEL}
+    provider_id: meta-reference-inference
+    model_type: llm
+  - metadata:
+      embedding_dimension: 768
+    model_id: nomic-embed-text-v1.5
+    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
+server:
+  port: 8321
+telemetry:
+  enabled: true