phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-05 18:27:22 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

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

Browse source 
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 .`
This commit is contained in:
Ashwin Bharambe 2025-10-27 12:02:21 -07:00 • committed by GitHub
parent 98a5047f9d
commit 471b1b248b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
791 changed files with 2983 additions and 456 deletions
Download patch file Download diff file Expand all files Collapse all files

7
src/llama_stack/distributions/dell/__init__.py Normal file
View file

@ -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 .dell import get_distribution_template # noqa: F401

33
src/llama_stack/distributions/dell/build.yaml Normal file
View file

@ -0,0 +1,33 @@
version: 2
distribution_spec:
description: Dell's distribution of Llama Stack. TGI inference via Dell's custom
container
providers:
inference:
- provider_type: remote::tgi
- provider_type: inline::sentence-transformers
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
image_type: venv
additional_pip_packages:
- aiosqlite
- sqlalchemy[asyncio]

158
src/llama_stack/distributions/dell/dell.py Normal file
View file

@ -0,0 +1,158 @@
# 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 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.sentence_transformers import (
SentenceTransformersInferenceConfig,
)
from llama_stack.providers.remote.vector_io.chroma import ChromaVectorIOConfig
def get_distribution_template() -> DistributionTemplate:
providers = {
"inference": [
BuildProvider(provider_type="remote::tgi"),
BuildProvider(provider_type="inline::sentence-transformers"),
],
"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"),
],
}
name = "dell"
inference_provider = Provider(
provider_id="tgi0",
provider_type="remote::tgi",
config={
"url": "${env.DEH_URL}",
},
)
safety_inference_provider = Provider(
provider_id="tgi1",
provider_type="remote::tgi",
config={
"url": "${env.DEH_SAFETY_URL}",
},
)
embedding_provider = Provider(
provider_id="sentence-transformers",
provider_type="inline::sentence-transformers",
config=SentenceTransformersInferenceConfig.sample_run_config(),
)
chromadb_provider = Provider(
provider_id="chromadb",
provider_type="remote::chromadb",
config=ChromaVectorIOConfig.sample_run_config(
f"~/.llama/distributions/{name}/",
url="${env.CHROMADB_URL:=}",
),
)
inference_model = ModelInput(
model_id="${env.INFERENCE_MODEL}",
provider_id="tgi0",
)
safety_model = ModelInput(
model_id="${env.SAFETY_MODEL}",
provider_id="tgi1",
)
embedding_model = ModelInput(
model_id="nomic-embed-text-v1.5",
provider_id="sentence-transformers",
model_type=ModelType.embedding,
metadata={
"embedding_dimension": 768,
},
)
default_tool_groups = [
ToolGroupInput(
toolgroup_id="builtin::websearch",
provider_id="brave-search",
),
ToolGroupInput(
toolgroup_id="builtin::rag",
provider_id="rag-runtime",
),
]
return DistributionTemplate(
name=name,
distro_type="self_hosted",
description="Dell's distribution of Llama Stack. TGI inference via Dell's custom container",
container_image=None,
providers=providers,
run_configs={
"run.yaml": RunConfigSettings(
provider_overrides={
"inference": [inference_provider, embedding_provider],
"vector_io": [chromadb_provider],
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
"inference": [
inference_provider,
safety_inference_provider,
embedding_provider,
],
"vector_io": [chromadb_provider],
},
default_models=[inference_model, safety_model, embedding_model],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}")],
default_tool_groups=default_tool_groups,
),
},
run_config_env_vars={
"DEH_URL": (
"http://0.0.0.0:8181",
"URL for the Dell inference server",
),
"DEH_SAFETY_URL": (
"http://0.0.0.0:8282",
"URL for the Dell safety inference server",
),
"CHROMA_URL": (
"http://localhost:6601",
"URL for the Chroma server",
),
"INFERENCE_MODEL": (
"meta-llama/Llama-3.2-3B-Instruct",
"Inference model loaded into the TGI server",
),
"SAFETY_MODEL": (
"meta-llama/Llama-Guard-3-1B",
"Name of the safety (Llama-Guard) model to use",
),
},
)

178
src/llama_stack/distributions/dell/doc_template.md Normal file
View file

@ -0,0 +1,178 @@
---
orphan: true
---
# Dell Distribution of Llama Stack
```{toctree}
:maxdepth: 2
:hidden:
self
```
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
{{ providers_table }}
You can use this distribution if you have GPUs and want to run an independent TGI or Dell Enterprise Hub container for running inference.
{% 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 %}
## Setting up Inference server using Dell Enterprise Hub's custom TGI container.
NOTE: This is a placeholder to run inference with TGI. This will be updated to use [Dell Enterprise Hub's containers](https://dell.huggingface.co/authenticated/models) once verified.
```bash
export INFERENCE_PORT=8181
export DEH_URL=http://0.0.0.0:$INFERENCE_PORT
export INFERENCE_MODEL=meta-llama/Llama-3.1-8B-Instruct
export CHROMADB_HOST=localhost
export CHROMADB_PORT=6601
export CHROMA_URL=http://$CHROMADB_HOST:$CHROMADB_PORT
export CUDA_VISIBLE_DEVICES=0
export LLAMA_STACK_PORT=8321
docker run --rm -it \
--pull always \
--network host \
-v $HOME/.cache/huggingface:/data \
-e HF_TOKEN=$HF_TOKEN \
-p $INFERENCE_PORT:$INFERENCE_PORT \
--gpus $CUDA_VISIBLE_DEVICES \
ghcr.io/huggingface/text-generation-inference \
--dtype bfloat16 \
--usage-stats off \
--sharded false \
--cuda-memory-fraction 0.7 \
--model-id $INFERENCE_MODEL \
--port $INFERENCE_PORT --hostname 0.0.0.0
```
If you are using Llama Stack Safety / Shield APIs, then you will need to also run another instance of a TGI with a corresponding safety model like `meta-llama/Llama-Guard-3-1B` using a script like:
```bash
export SAFETY_INFERENCE_PORT=8282
export DEH_SAFETY_URL=http://0.0.0.0:$SAFETY_INFERENCE_PORT
export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
export CUDA_VISIBLE_DEVICES=1
docker run --rm -it \
--pull always \
--network host \
-v $HOME/.cache/huggingface:/data \
-e HF_TOKEN=$HF_TOKEN \
-p $SAFETY_INFERENCE_PORT:$SAFETY_INFERENCE_PORT \
--gpus $CUDA_VISIBLE_DEVICES \
ghcr.io/huggingface/text-generation-inference \
--dtype bfloat16 \
--usage-stats off \
--sharded false \
--cuda-memory-fraction 0.7 \
--model-id $SAFETY_MODEL \
--hostname 0.0.0.0 \
--port $SAFETY_INFERENCE_PORT
```
## Dell distribution relies on ChromaDB for vector database usage
You can start a chroma-db easily using docker.
```bash
# This is where the indices are persisted
mkdir -p $HOME/chromadb
podman run --rm -it \
--network host \
--name chromadb \
-v $HOME/chromadb:/chroma/chroma \
-e IS_PERSISTENT=TRUE \
chromadb/chroma:latest \
--port $CHROMADB_PORT \
--host $CHROMADB_HOST
```
## Running Llama Stack
Now you are ready to run Llama Stack with TGI as the inference provider. 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
docker run -it \
--pull always \
--network host \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v $HOME/.llama:/root/.llama \
# NOTE: mount the llama-stack directory if testing local changes else not needed
-v $HOME/git/llama-stack:/app/llama-stack-source \
# localhost/distribution-dell:dev if building / testing locally
-e INFERENCE_MODEL=$INFERENCE_MODEL \
-e DEH_URL=$DEH_URL \
-e CHROMA_URL=$CHROMA_URL \
llamastack/distribution-{{ name }}\
--port $LLAMA_STACK_PORT
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
# You need a local checkout of llama-stack to run this, get it using
# git clone https://github.com/meta-llama/llama-stack.git
cd /path/to/llama-stack
export SAFETY_INFERENCE_PORT=8282
export DEH_SAFETY_URL=http://0.0.0.0:$SAFETY_INFERENCE_PORT
export SAFETY_MODEL=meta-llama/Llama-Guard-3-1B
docker run \
-it \
--pull always \
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT \
-v $HOME/.llama:/root/.llama \
-v ./llama_stack/distributions/tgi/run-with-safety.yaml:/root/my-run.yaml \
-e INFERENCE_MODEL=$INFERENCE_MODEL \
-e DEH_URL=$DEH_URL \
-e SAFETY_MODEL=$SAFETY_MODEL \
-e DEH_SAFETY_URL=$DEH_SAFETY_URL \
-e CHROMA_URL=$CHROMA_URL \
llamastack/distribution-{{ name }} \
--config /root/my-run.yaml \
--port $LLAMA_STACK_PORT
```
### Via Conda
Make sure you have done `pip install llama-stack` and have the Llama Stack CLI available.
```bash
llama stack list-deps {{ name }} | xargs -L1 pip install
INFERENCE_MODEL=$INFERENCE_MODEL \
DEH_URL=$DEH_URL \
CHROMA_URL=$CHROMA_URL \
llama stack run {{ name }} \
--port $LLAMA_STACK_PORT
```
If you are using Llama Stack Safety / Shield APIs, use:
```bash
INFERENCE_MODEL=$INFERENCE_MODEL \
DEH_URL=$DEH_URL \
SAFETY_MODEL=$SAFETY_MODEL \
DEH_SAFETY_URL=$DEH_SAFETY_URL \
CHROMA_URL=$CHROMA_URL \
llama stack run ./run-with-safety.yaml \
--port $LLAMA_STACK_PORT
```

141
src/llama_stack/distributions/dell/run-with-safety.yaml Normal file
View file

@ -0,0 +1,141 @@
version: 2
image_name: dell
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- tool_runtime
- vector_io
providers:
inference:
- provider_id: tgi0
provider_type: remote::tgi
config:
url: ${env.DEH_URL}
- provider_id: tgi1
provider_type: remote::tgi
config:
url: ${env.DEH_SAFETY_URL}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:=}
persistence:
namespace: vector_io::chroma_remote
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
storage:
backends:
kv_default:
type: kv_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/kvstore.db
sql_default:
type: sql_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/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: tgi0
model_type: llm
- metadata: {}
model_id: ${env.SAFETY_MODEL}
provider_id: tgi1
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: brave-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
server:
port: 8321
telemetry:
enabled: true

135
src/llama_stack/distributions/dell/run.yaml Normal file
View file

@ -0,0 +1,135 @@
version: 2
image_name: dell
apis:
- agents
- datasetio
- eval
- inference
- safety
- scoring
- tool_runtime
- vector_io
providers:
inference:
- provider_id: tgi0
provider_type: remote::tgi
config:
url: ${env.DEH_URL}
- provider_id: sentence-transformers
provider_type: inline::sentence-transformers
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL:=}
persistence:
namespace: vector_io::chroma_remote
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
storage:
backends:
kv_default:
type: kv_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/kvstore.db
sql_default:
type: sql_sqlite
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/dell}/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: tgi0
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: brave-search
- toolgroup_id: builtin::rag
provider_id: rag-runtime
server:
port: 8321
telemetry:
enabled: true