phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2026-01-03 04:32:15 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge-related changes.

Browse source
This commit is contained in:
ilya-kolchinsky 2025-04-02 19:56:44 +02:00
commit 60e9f46856
456 changed files with 38636 additions and 10892 deletions
Download patch file Download diff file Expand all files Collapse all files

94
llama_stack/templates/nvidia/nvidia.py
View file

@ -7,9 +7,10 @@
from pathlib import Path
from llama_stack.apis.preprocessing.preprocessors import PreprocessorInput
from llama_stack.distribution.datatypes import Provider, ToolGroupInput
from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput, ToolGroupInput
from llama_stack.providers.remote.inference.nvidia import NVIDIAConfig
from llama_stack.providers.remote.inference.nvidia.models import MODEL_ENTRIES
from llama_stack.providers.remote.safety.nvidia import NVIDIASafetyConfig
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings, get_model_registry
@ -17,19 +18,14 @@ def get_distribution_template() -> DistributionTemplate:
providers = {
"inference": ["remote::nvidia"],
"vector_io": ["inline::faiss"],
"safety": ["inline::llama-guard"],
"safety": ["remote::nvidia"],
"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",
],
"post_training": ["remote::nvidia"],
"datasetio": ["inline::localfs"],
"scoring": ["inline::basic"],
"tool_runtime": ["inline::rag-runtime"],
"preprocessing": ["inline::basic", "inline::simple_chunking"],
}
@ -38,23 +34,28 @@ def get_distribution_template() -> DistributionTemplate:
provider_type="remote::nvidia",
config=NVIDIAConfig.sample_run_config(),
)
safety_provider = Provider(
provider_id="nvidia",
provider_type="remote::nvidia",
config=NVIDIASafetyConfig.sample_run_config(),
)
inference_model = ModelInput(
model_id="${env.INFERENCE_MODEL}",
provider_id="nvidia",
)
safety_model = ModelInput(
model_id="${env.SAFETY_MODEL}",
provider_id="nvidia",
)
available_models = {
"nvidia": MODEL_ENTRIES,
}
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",
),
]
default_preprocessors = [
PreprocessorInput(
@ -71,7 +72,7 @@ def get_distribution_template() -> DistributionTemplate:
return DistributionTemplate(
name="nvidia",
distro_type="remote_hosted",
description="Use NVIDIA NIM for running LLM inference",
description="Use NVIDIA NIM for running LLM inference and safety",
container_image=None,
template_path=Path(__file__).parent / "doc_template.md",
providers=providers,
@ -85,15 +86,60 @@ def get_distribution_template() -> DistributionTemplate:
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
"run-with-safety.yaml": RunConfigSettings(
provider_overrides={
"inference": [
inference_provider,
safety_provider,
]
},
default_models=[inference_model, safety_model],
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}", provider_id="nvidia")],
default_tool_groups=default_tool_groups,
default_preprocessors=default_preprocessors,
),
},
run_config_env_vars={
"LLAMASTACK_PORT": (
"5001",
"Port for the Llama Stack distribution server",
),
"NVIDIA_API_KEY": (
"",
"NVIDIA API Key",
),
## Nemo Customizer related variables
"NVIDIA_USER_ID": (
"llama-stack-user",
"NVIDIA User ID",
),
"NVIDIA_DATASET_NAMESPACE": (
"default",
"NVIDIA Dataset Namespace",
),
"NVIDIA_ACCESS_POLICIES": (
"{}",
"NVIDIA Access Policies",
),
"NVIDIA_PROJECT_ID": (
"test-project",
"NVIDIA Project ID",
),
"NVIDIA_CUSTOMIZER_URL": (
"https://customizer.api.nvidia.com",
"NVIDIA Customizer URL",
),
"NVIDIA_OUTPUT_MODEL_DIR": (
"test-example-model@v1",
"NVIDIA Output Model Directory",
),
"GUARDRAILS_SERVICE_URL": (
"http://0.0.0.0:7331",
"URL for the NeMo Guardrails Service",
),
"INFERENCE_MODEL": (
"Llama3.1-8B-Instruct",
"Inference model",
),
"SAFETY_MODEL": (
"meta/llama-3.1-8b-instruct",
"Name of the model to use for safety",
),
},
)