phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-05 09:02:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

cerebras fix

Browse source
This commit is contained in:
Xi Yan 2025-01-16 17:33:20 -08:00
parent 73215460ba
commit 11e9614e2e
1 changed files with 8 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/templates/cerebras/cerebras.py
View file

@ -18,6 +18,7 @@ from llama_stack.distribution.datatypes import (
from llama_stack.providers.inline.inference.sentence_transformers import ( from llama_stack.providers.inline.inference.sentence_transformers import (
SentenceTransformersInferenceConfig, SentenceTransformersInferenceConfig,
) )
from llama_stack.providers.inline.memory.faiss.config import FaissImplConfig
from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig from llama_stack.providers.remote.inference.cerebras import CerebrasImplConfig
from llama_stack.providers.remote.inference.cerebras.cerebras import model_aliases from llama_stack.providers.remote.inference.cerebras.cerebras import model_aliases
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
@ -41,6 +42,7 @@ def get_distribution_template() -> DistributionTemplate:
], ],
} }
name = "cerebras"
inference_provider = Provider( inference_provider = Provider(
provider_id="cerebras", provider_id="cerebras",
provider_type="remote::cerebras", provider_type="remote::cerebras",
@ -71,6 +73,11 @@ def get_distribution_template() -> DistributionTemplate:
"embedding_dimension": 384, "embedding_dimension": 384,
}, },
) )
memory_provider = Provider(
provider_id="faiss",
provider_type="inline::faiss",
config=FaissImplConfig.sample_run_config(f"distributions/{name}"),
)
default_tool_groups = [ default_tool_groups = [
ToolGroupInput( ToolGroupInput(
toolgroup_id="builtin::websearch", toolgroup_id="builtin::websearch",
@ -98,6 +105,7 @@ def get_distribution_template() -> DistributionTemplate:
"run.yaml": RunConfigSettings( "run.yaml": RunConfigSettings(
provider_overrides={ provider_overrides={
"inference": [inference_provider, embedding_provider], "inference": [inference_provider, embedding_provider],
"memory": [memory_provider],
}, },
default_models=default_models + [embedding_model], default_models=default_models + [embedding_model],
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")], default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],