phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 02:12:26 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

all templates to include toolgroups and tool runtime

Browse source
This commit is contained in:
Dinesh Yeduguru 2025-01-08 15:28:03 -08:00
parent 67b35613bb
commit edcfd66be3
55 changed files with 854 additions and 145 deletions
Download patch file Download diff file Expand all files Collapse all files

24
llama_stack/templates/meta-reference-quantized-gpu/meta_reference.py
View file

@ -7,8 +7,7 @@
from pathlib import Path
from llama_stack.apis.models.models import ModelType
from llama_stack.distribution.datatypes import ModelInput, Provider
from llama_stack.distribution.datatypes import ModelInput, Provider, ToolGroupInput
from llama_stack.providers.inline.inference.meta_reference import (
MetaReferenceQuantizedInferenceConfig,
)
@ -29,7 +28,27 @@ def get_distribution_template() -> DistributionTemplate:
"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::memory-runtime",
],
}
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",
),
]
name = "meta-reference-quantized-gpu"
inference_provider = Provider(
provider_id="meta-reference-inference",
@ -76,6 +95,7 @@ def get_distribution_template() -> DistributionTemplate:
"memory": [memory_provider],
},
default_models=[inference_model, embedding_model],
default_tool_groups=default_tool_groups,
),
},
run_config_env_vars={