forked from phoenix-oss/llama-stack-mirror
115 lines
4.2 KiB
Python
115 lines
4.2 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_stack.apis.models.models import ModelType
|
|
from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
|
|
from llama_stack.providers.inline.inference.meta_reference import (
|
|
MetaReferenceQuantizedInferenceConfig,
|
|
)
|
|
from llama_stack.providers.inline.inference.sentence_transformers import (
|
|
SentenceTransformersInferenceConfig,
|
|
)
|
|
from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig
|
|
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
|
|
|
|
|
def get_distribution_template() -> DistributionTemplate:
|
|
providers = {
|
|
"inference": ["inline::meta-reference-quantized"],
|
|
"vector_io": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
|
|
"safety": ["inline::llama-guard"],
|
|
"agents": ["inline::meta-reference"],
|
|
"telemetry": ["inline::meta-reference"],
|
|
"eval": ["inline::meta-reference"],
|
|
"datasetio": ["remote::huggingface", "inline::localfs"],
|
|
"scoring": ["inline::basic", "inline::llm-as-judge", "inline::braintrust"],
|
|
"tool_runtime": [
|
|
"remote::brave-search",
|
|
"remote::tavily-search",
|
|
"inline::code-interpreter",
|
|
"inline::rag-runtime",
|
|
"remote::model-context-protocol",
|
|
],
|
|
}
|
|
default_tool_groups = [
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::websearch",
|
|
provider_id="tavily-search",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::rag",
|
|
provider_id="rag-runtime",
|
|
),
|
|
ToolGroupInput(
|
|
toolgroup_id="builtin::code_interpreter",
|
|
provider_id="code-interpreter",
|
|
),
|
|
]
|
|
name = "meta-reference-quantized-gpu"
|
|
inference_provider = Provider(
|
|
provider_id="meta-reference-inference",
|
|
provider_type="inline::meta-reference-quantized",
|
|
config=MetaReferenceQuantizedInferenceConfig.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="all-MiniLM-L6-v2",
|
|
provider_id="sentence-transformers",
|
|
model_type=ModelType.embedding,
|
|
metadata={
|
|
"embedding_dimension": 384,
|
|
},
|
|
)
|
|
return DistributionTemplate(
|
|
name=name,
|
|
distro_type="self_hosted",
|
|
description="Use Meta Reference with fp8, int4 quantization 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_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",
|
|
),
|
|
},
|
|
)
|