phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 09:30:03 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Updated the configuration templates to include the builtin preprocessors.

Browse source
This commit is contained in:
ilya-kolchinsky 2025-03-07 16:08:14 +01:00
parent e895bb111c
commit 3f15349c9d
72 changed files with 632 additions and 25 deletions
Download patch file Download diff file Expand all files Collapse all files

13
llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
View file

@ -7,6 +7,7 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessing.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
from llama_stack.providers.inline.inference.meta_reference import (
MetaReferenceQuantizedInferenceConfig,
@ -35,6 +36,7 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
default_tool_groups = [
ToolGroupInput(
@ -50,6 +52,16 @@ def get_distribution_template() -> DistributionTemplate:
provider_id="code-interpreter",
),
]
default_preprocessors = [
PreprocessorInput(
preprocessor_id="builtin::basic",
provider_id="basic",
),
PreprocessorInput(
preprocessor_id="builtin::chunking",
provider_id="simple_chunking",
),
]
name = "meta-reference-quantized-gpu"
inference_provider = Provider(
provider_id="meta-reference-inference",
@ -96,6 +108,7 @@ def get_distribution_template() -> DistributionTemplate:
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={