mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-13 18:02:37 +00:00
chore(package): migrate to src/ layout
Moved package code from llama_stack/ to src/llama_stack/ following Python packaging best practices. Updated pyproject.toml, MANIFEST.in, and tool configurations accordingly. Public API and import paths remain unchanged. Developers will need to reinstall in editable mode after pulling this change. Also updated paths in pre-commit config, scripts, and GitHub workflows.
This commit is contained in:
Ashwin Bharambe
parent
98a5047f9d
commit
8e5ed739ec
790 changed files with 2947 additions and 447 deletions
|
|
@ -1,7 +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 .meta_reference import get_distribution_template # noqa: F401
|
||||
|
|
@ -1,89 +0,0 @@
|
|||
---
|
||||
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
|
||||
```
|
||||
|
|
@ -1,163 +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 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",
|
||||
),
|
||||
},
|
||||
)
|
||||
Loading…
Add table
Add a link
Reference in a new issue