Update more distribution docs to be simpler and partially codegen'ed

llama_stack/templates/meta-reference-quantized-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

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

@@ -0,0 +1,54 @@
+# Meta Reference Quantized Distribution
+
+The `llamastack/distribution-meta-reference-quantized-gpu` distribution consists of the following provider configurations.
+
+
+| **API**         	| **Inference**            	| **Agents**     	| **Memory**                                       	| **Safety**     	| **Telemetry**  	|
+|-----------------	|------------------------  	|----------------	|--------------------------------------------------	|----------------	|----------------	|
+| **Provider(s)** 	| meta-reference-quantized  | meta-reference 	| meta-reference, remote::pgvector, remote::chroma 	| meta-reference 	| meta-reference 	|
+
+The only difference vs. the `meta-reference-gpu` distribution is that it has support for more efficient inference -- with fp8, int4 quantization, etc.
+
+### Step 0. Prerequisite - Downloading Models
+Please make sure you have llama model checkpoints downloaded in `~/.llama` before proceeding. See [installation guide](https://llama-stack.readthedocs.io/en/latest/cli_reference/download_models.html) here to download the models.
+
+```
+$ ls ~/.llama/checkpoints
+Llama3.2-3B-Instruct:int4-qlora-eo8
+```
+
+### Step 1. Start the Distribution
+#### (Option 1) Start with Docker
+```
+$ cd distributions/meta-reference-quantized-gpu && docker compose up
+```
+
+> [!NOTE]
+> This assumes you have access to GPU to start a local server with access to your GPU.
+
+
+> [!NOTE]
+> `~/.llama` should be the path containing downloaded weights of Llama models.
+
+
+This will download and start running a pre-built docker container. Alternatively, you may use the following commands:
+
+```
+docker run -it -p 5000:5000 -v ~/.llama:/root/.llama -v ./run.yaml:/root/my-run.yaml --gpus=all distribution-meta-reference-quantized-gpu --yaml_config /root/my-run.yaml
+```
+
+#### (Option 2) Start with Conda
+
+1. Install the `llama` CLI. See [CLI Reference](https://llama-stack.readthedocs.io/en/latest/cli_reference/index.html)
+
+2. Build the `meta-reference-quantized-gpu` distribution
+
+```
+$ llama stack build --template meta-reference-quantized-gpu --image-type conda
+```
+
+3. Start running distribution
+```
+$ cd distributions/meta-reference-quantized-gpu
+$ llama stack run ./run.yaml
+```

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

@@ -0,0 +1,100 @@
+# 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.distribution.datatypes import ModelInput, Provider, ShieldInput
+from llama_stack.providers.inline.inference.meta_reference import (
+    MetaReferenceInferenceConfig,
+)
+from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
+
+
+def get_distribution_template() -> DistributionTemplate:
+    providers = {
+        "inference": ["inline::meta-reference"],
+        "memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
+        "safety": ["inline::llama-guard"],
+        "agents": ["inline::meta-reference"],
+        "telemetry": ["inline::meta-reference"],
+    }
+
+    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}",
+        ),
+    )
+
+    inference_model = ModelInput(
+        model_id="${env.INFERENCE_MODEL}",
+        provider_id="meta-reference-inference",
+    )
+    safety_model = ModelInput(
+        model_id="${env.SAFETY_MODEL}",
+        provider_id="meta-reference-safety",
+    )
+
+    return DistributionTemplate(
+        name="meta-reference-gpu",
+        distro_type="self_hosted",
+        description="Use Meta Reference for running LLM inference",
+        template_path=Path(__file__).parent / "doc_template.md",
+        providers=providers,
+        default_models=[inference_model, safety_model],
+        run_configs={
+            "run.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [inference_provider],
+                },
+                default_models=[inference_model],
+            ),
+            "run-with-safety.yaml": RunConfigSettings(
+                provider_overrides={
+                    "inference": [
+                        inference_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}",
+                            ),
+                        ),
+                    ],
+                },
+                default_models=[
+                    inference_model,
+                    safety_model,
+                ],
+                default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
+            ),
+        },
+        run_config_env_vars={
+            "LLAMASTACK_PORT": (
+                "5001",
+                "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",
+            ),
+        },
+    )