mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-27 06:28:50 +00:00
feat: consolidate most distros into "starter" (#2516)
# What does this PR do? * Removes a bunch of distros * Removed distros were added into the "starter" distribution * Doc for "starter" has been added * Partially reverts https://github.com/meta-llama/llama-stack/pull/2482 since inference providers are disabled by default and can be turned on manually via env variable. * Disables safety in starter distro Closes: https://github.com/meta-llama/llama-stack/issues/2502. ~Needs: https://github.com/meta-llama/llama-stack/pull/2482 for Ollama to work properly in the CI.~ TODO: - [ ] We can only update `install.sh` when we get a new release. - [x] Update providers documentation - [ ] Update notebooks to reference starter instead of ollama Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han
GitHub
parent
f77d4d91f5
commit
c4349f532b
132 changed files with 1009 additions and 10845 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 .cerebras import get_distribution_template # noqa: F401
|
||||
|
|
@ -1,34 +0,0 @@
|
|||
version: 2
|
||||
distribution_spec:
|
||||
description: Use Cerebras for running LLM inference
|
||||
providers:
|
||||
inference:
|
||||
- remote::cerebras
|
||||
- inline::sentence-transformers
|
||||
safety:
|
||||
- inline::llama-guard
|
||||
vector_io:
|
||||
- inline::faiss
|
||||
- remote::chromadb
|
||||
- remote::pgvector
|
||||
agents:
|
||||
- inline::meta-reference
|
||||
eval:
|
||||
- inline::meta-reference
|
||||
datasetio:
|
||||
- remote::huggingface
|
||||
- inline::localfs
|
||||
scoring:
|
||||
- inline::basic
|
||||
- inline::llm-as-judge
|
||||
- inline::braintrust
|
||||
telemetry:
|
||||
- inline::meta-reference
|
||||
tool_runtime:
|
||||
- remote::brave-search
|
||||
- remote::tavily-search
|
||||
- inline::rag-runtime
|
||||
image_type: conda
|
||||
additional_pip_packages:
|
||||
- aiosqlite
|
||||
- sqlalchemy[asyncio]
|
||||
|
|
@ -1,110 +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.distribution.datatypes import ModelInput, Provider, ToolGroupInput
|
||||
from llama_stack.providers.inline.inference.sentence_transformers import (
|
||||
SentenceTransformersInferenceConfig,
|
||||
)
|
||||
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
|
||||
from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig
|
||||
from llama_stack.providers.remote.inference.cerebras.models import MODEL_ENTRIES
|
||||
from llama_stack.templates.template import (
|
||||
DistributionTemplate,
|
||||
RunConfigSettings,
|
||||
get_model_registry,
|
||||
)
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": ["remote::cerebras", "inline::sentence-transformers"],
|
||||
"safety": ["inline::llama-guard"],
|
||||
"vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"eval": ["inline::meta-reference"],
|
||||
"datasetio": ["remote::huggingface", "inline::localfs"],
|
||||
"scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
"tool_runtime": [
|
||||
"remote::brave-search",
|
||||
"remote::tavily-search",
|
||||
"inline::rag-runtime",
|
||||
],
|
||||
}
|
||||
|
||||
name = "cerebras"
|
||||
inference_provider = Provider(
|
||||
provider_id="cerebras",
|
||||
provider_type="remote::cerebras",
|
||||
config=CerebrasImplConfig.sample_run_config(),
|
||||
)
|
||||
embedding_provider = Provider(
|
||||
provider_id="sentence-transformers",
|
||||
provider_type="inline::sentence-transformers",
|
||||
config=SentenceTransformersInferenceConfig.sample_run_config(),
|
||||
)
|
||||
|
||||
available_models = {
|
||||
"cerebras": MODEL_ENTRIES,
|
||||
}
|
||||
default_models = get_model_registry(available_models)
|
||||
embedding_model = ModelInput(
|
||||
model_id="all-MiniLM-L6-v2",
|
||||
provider_id="sentence-transformers",
|
||||
model_type=ModelType.embedding,
|
||||
metadata={
|
||||
"embedding_dimension": 384,
|
||||
},
|
||||
)
|
||||
vector_io_provider = Provider(
|
||||
provider_id="faiss",
|
||||
provider_type="inline::faiss",
|
||||
config=FaissVectorIOConfig.sample_run_config(f"~/.llama/distributions/{name}"),
|
||||
)
|
||||
default_tool_groups = [
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::websearch",
|
||||
provider_id="tavily-search",
|
||||
),
|
||||
ToolGroupInput(
|
||||
toolgroup_id="builtin::rag",
|
||||
provider_id="rag-runtime",
|
||||
),
|
||||
]
|
||||
|
||||
return DistributionTemplate(
|
||||
name="cerebras",
|
||||
distro_type="self_hosted",
|
||||
description="Use Cerebras for running LLM inference",
|
||||
container_image=None,
|
||||
template_path=Path(__file__).parent / "doc_template.md",
|
||||
providers=providers,
|
||||
available_models_by_provider=available_models,
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [inference_provider, embedding_provider],
|
||||
"vector_io": [vector_io_provider],
|
||||
},
|
||||
default_models=default_models + [embedding_model],
|
||||
default_shields=[],
|
||||
default_tool_groups=default_tool_groups,
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMA_STACK_PORT": (
|
||||
"8321",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
"CEREBRAS_API_KEY": (
|
||||
"",
|
||||
"Cerebras API Key",
|
||||
),
|
||||
},
|
||||
)
|
||||
|
|
@ -1,61 +0,0 @@
|
|||
# Cerebras Distribution
|
||||
|
||||
The `llamastack/distribution-{{ name }}` distribution consists of the following provider configurations.
|
||||
|
||||
{{ providers_table }}
|
||||
|
||||
{% 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 %}
|
||||
|
||||
{% if default_models %}
|
||||
### Models
|
||||
|
||||
The following models are available by default:
|
||||
|
||||
{% for model in default_models %}
|
||||
- `{{ model.model_id }} {{ model.doc_string }}`
|
||||
{% endfor %}
|
||||
{% endif %}
|
||||
|
||||
|
||||
### Prerequisite: API Keys
|
||||
|
||||
Make sure you have access to a Cerebras API Key. You can get one by visiting [cloud.cerebras.ai](https://cloud.cerebras.ai/).
|
||||
|
||||
|
||||
## Running Llama Stack with Cerebras
|
||||
|
||||
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 ./run.yaml:/root/my-run.yaml \
|
||||
llamastack/distribution-{{ name }} \
|
||||
--config /root/my-run.yaml \
|
||||
--port $LLAMA_STACK_PORT \
|
||||
--env CEREBRAS_API_KEY=$CEREBRAS_API_KEY
|
||||
```
|
||||
|
||||
### Via Conda
|
||||
|
||||
```bash
|
||||
llama stack build --template cerebras --image-type conda
|
||||
llama stack run ./run.yaml \
|
||||
--port 8321 \
|
||||
--env CEREBRAS_API_KEY=$CEREBRAS_API_KEY
|
||||
```
|
||||
|
|
@ -1,140 +0,0 @@
|
|||
version: 2
|
||||
image_name: cerebras
|
||||
apis:
|
||||
- agents
|
||||
- datasetio
|
||||
- eval
|
||||
- inference
|
||||
- safety
|
||||
- scoring
|
||||
- telemetry
|
||||
- tool_runtime
|
||||
- vector_io
|
||||
providers:
|
||||
inference:
|
||||
- provider_id: cerebras
|
||||
provider_type: remote::cerebras
|
||||
config:
|
||||
base_url: https://api.cerebras.ai
|
||||
api_key: ${env.CEREBRAS_API_KEY}
|
||||
- provider_id: sentence-transformers
|
||||
provider_type: inline::sentence-transformers
|
||||
config: {}
|
||||
safety:
|
||||
- provider_id: llama-guard
|
||||
provider_type: inline::llama-guard
|
||||
config:
|
||||
excluded_categories: []
|
||||
vector_io:
|
||||
- provider_id: faiss
|
||||
provider_type: inline::faiss
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/cerebras}/faiss_store.db
|
||||
agents:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
persistence_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/cerebras}/agents_store.db
|
||||
responses_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/cerebras}/responses_store.db
|
||||
eval:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/cerebras}/meta_reference_eval.db
|
||||
datasetio:
|
||||
- provider_id: huggingface
|
||||
provider_type: remote::huggingface
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/cerebras}/huggingface_datasetio.db
|
||||
- provider_id: localfs
|
||||
provider_type: inline::localfs
|
||||
config:
|
||||
kvstore:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/cerebras}/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: ${env.OPENAI_API_KEY:=}
|
||||
telemetry:
|
||||
- provider_id: meta-reference
|
||||
provider_type: inline::meta-reference
|
||||
config:
|
||||
service_name: "${env.OTEL_SERVICE_NAME:=\u200B}"
|
||||
sinks: ${env.TELEMETRY_SINKS:=console,sqlite}
|
||||
sqlite_db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/cerebras}/trace_store.db
|
||||
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
|
||||
config: {}
|
||||
metadata_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/cerebras}/registry.db
|
||||
inference_store:
|
||||
type: sqlite
|
||||
db_path: ${env.SQLITE_STORE_DIR:=~/.llama/distributions/cerebras}/inference_store.db
|
||||
models:
|
||||
- metadata: {}
|
||||
model_id: llama3.1-8b
|
||||
provider_id: cerebras
|
||||
provider_model_id: llama3.1-8b
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.1-8B-Instruct
|
||||
provider_id: cerebras
|
||||
provider_model_id: llama3.1-8b
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: llama-3.3-70b
|
||||
provider_id: cerebras
|
||||
provider_model_id: llama-3.3-70b
|
||||
model_type: llm
|
||||
- metadata: {}
|
||||
model_id: meta-llama/Llama-3.3-70B-Instruct
|
||||
provider_id: cerebras
|
||||
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: []
|
||||
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
|
||||
Loading…
Add table
Add a link
Reference in a new issue