phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-02 05:04:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Restrict the changes to the new preprocessing API only.

Browse source
This commit is contained in:
ilya-kolchinsky 2025-04-03 12:19:08 +02:00
parent 2008cd7921
commit 863f87aa15
90 changed files with 104 additions and 1138 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

@ -7,7 +7,6 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.apis.preprocessors.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
from llama_stack.providers.inline.inference.meta_reference import (
MetaReferenceQuantizedInferenceConfig,
@ -36,7 +35,6 @@ def get_distribution_template() -> DistributionTemplate:
"inline::rag-runtime",
"remote::model-context-protocol",
],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
default_tool_groups = [
ToolGroupInput(
@ -52,16 +50,6 @@ 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",
@ -108,7 +96,6 @@ 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={