mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-28 02:53:30 +00:00
d1f3b032c9
# What does this PR do? - we no longer have meta-reference as memory provider, update cerebras template ## Test Plan ``` python llama_stack/scripts/distro_codegen.py ``` ## Sources Please link relevant resources if necessary. ## Before submitting - [ ] This PR fixes a typo or improves the docs (you can dismiss the other checks if that's the case). - [ ] Ran pre-commit to handle lint / formatting issues. - [ ] Read the [contributor guideline](https://github.com/meta-llama/llama-stack/blob/main/CONTRIBUTING.md), Pull Request section? - [ ] Updated relevant documentation. - [ ] Wrote necessary unit or integration tests.
117 lines
3.9 KiB
Python
117 lines
3.9 KiB
Python
# 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_models.sku_list import all_registered_models
|
|
|
|
from llama_stack.apis.models.models import ModelType
|
|
from llama_stack.distribution.datatypes import (
|
|
ModelInput,
|
|
Provider,
|
|
ShieldInput,
|
|
ToolGroupInput,
|
|
)
|
|
from llama_stack.providers.inline.inference.sentence_transformers import (
|
|
SentenceTransformersInferenceConfig,
|
|
)
|
|
from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig
|
|
from llama_stack.providers.remote.inference.cerebras.cerebras import model_aliases
|
|
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
|
|
|
|
|
def get_distribution_template() -> DistributionTemplate:
|
|
providers = {
|
|
"inference": ["remote::cerebras"],
|
|
"safety": ["inline::llama-guard"],
|
|
"memory": ["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::code-interpreter",
|
|
"inline::memory-runtime",
|
|
],
|
|
}
|
|
|
|
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(),
|
|
)
|
|
|
|
core_model_to_hf_repo = {
|
|
m.descriptor(): m.huggingface_repo for m in all_registered_models()
|
|
}
|
|
default_models = [
|
|
ModelInput(
|
|
model_id=core_model_to_hf_repo[m.llama_model],
|
|
provider_model_id=m.provider_model_id,
|
|
provider_id="cerebras",
|
|
)
|
|
for m in model_aliases
|
|
]
|
|
embedding_model = ModelInput(
|
|
model_id="all-MiniLM-L6-v2",
|
|
provider_id="sentence-transformers",
|
|
model_type=ModelType.embedding,
|
|
metadata={
|
|
"embedding_dimension": 384,
|
|
},
|
|
)
|
|
default_tool_groups = [
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::websearch",
|
|
provider_id="tavily-search",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::memory",
|
|
provider_id="memory-runtime",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::code_interpreter",
|
|
provider_id="code-interpreter",
|
|
),
|
|
]
|
|
|
|
return DistributionTemplate(
|
|
name="cerebras",
|
|
distro_type="self_hosted",
|
|
description="Use Cerebras for running LLM inference",
|
|
docker_image=None,
|
|
template_path=Path(__file__).parent / "doc_template.md",
|
|
providers=providers,
|
|
default_models=default_models,
|
|
run_configs={
|
|
"run.yaml": RunConfigSettings(
|
|
provider_overrides={
|
|
"inference": [inference_provider, embedding_provider],
|
|
},
|
|
default_models=default_models + [embedding_model],
|
|
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
|
|
default_tool_groups=default_tool_groups,
|
|
),
|
|
},
|
|
run_config_env_vars={
|
|
"LLAMA_STACK_PORT": (
|
|
"5001",
|
|
"Port for the Llama Stack distribution server",
|
|
),
|
|
"CEREBRAS_API_KEY": (
|
|
"",
|
|
"Cerebras API Key",
|
|
),
|
|
},
|
|
)
|