mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-14 09:06:10 +00:00
feat: consolidate most distros into "starter" (#2516)
# What does this PR do? * Removes a bunch of distros * Removed distros were added into the "starter" distribution * Doc for "starter" has been added * Partially reverts https://github.com/meta-llama/llama-stack/pull/2482 since inference providers are disabled by default and can be turned on manually via env variable. * Disables safety in starter distro Closes: https://github.com/meta-llama/llama-stack/issues/2502. ~Needs: https://github.com/meta-llama/llama-stack/pull/2482 for Ollama to work properly in the CI.~ TODO: - [ ] We can only update `install.sh` when we get a new release. - [x] Update providers documentation - [ ] Update notebooks to reference starter instead of ollama Signed-off-by: Sébastien Han <seb@redhat.com>
This commit is contained in:
Sébastien Han
GitHub
parent
f77d4d91f5
commit
c4349f532b
132 changed files with 1009 additions and 10845 deletions
|
|
@ -1,150 +0,0 @@
|
|||
# Copyright (c) Meta Platforms, Inc. and affiliates.
|
||||
# All rights reserved.
|
||||
#
|
||||
# This source code is licensed under the terms described in the LICENSE file in
|
||||
# the root directory of this source tree.
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
from llama_stack.distribution.datatypes import ModelInput, Provider, ShieldInput, ToolGroupInput
|
||||
from llama_stack.providers.remote.datasetio.nvidia import NvidiaDatasetIOConfig
|
||||
from llama_stack.providers.remote.eval.nvidia import NVIDIAEvalConfig
|
||||
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
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": ["remote::nvidia"],
|
||||
"vector_io": ["inline::faiss"],
|
||||
"safety": ["remote::nvidia"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
"eval": ["remote::nvidia"],
|
||||
"post_training": ["remote::nvidia"],
|
||||
"datasetio": ["inline::localfs", "remote::nvidia"],
|
||||
"scoring": ["inline::basic"],
|
||||
"tool_runtime": ["inline::rag-runtime"],
|
||||
}
|
||||
|
||||
inference_provider = Provider(
|
||||
provider_id="nvidia",
|
||||
provider_type="remote::nvidia",
|
||||
config=NVIDIAConfig.sample_run_config(),
|
||||
)
|
||||
safety_provider = Provider(
|
||||
provider_id="nvidia",
|
||||
provider_type="remote::nvidia",
|
||||
config=NVIDIASafetyConfig.sample_run_config(),
|
||||
)
|
||||
datasetio_provider = Provider(
|
||||
provider_id="nvidia",
|
||||
provider_type="remote::nvidia",
|
||||
config=NvidiaDatasetIOConfig.sample_run_config(),
|
||||
)
|
||||
eval_provider = Provider(
|
||||
provider_id="nvidia",
|
||||
provider_type="remote::nvidia",
|
||||
config=NVIDIAEvalConfig.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::rag",
|
||||
provider_id="rag-runtime",
|
||||
),
|
||||
]
|
||||
|
||||
default_models = get_model_registry(available_models)
|
||||
return DistributionTemplate(
|
||||
name="nvidia",
|
||||
distro_type="self_hosted",
|
||||
description="Use NVIDIA NIM for running LLM inference, evaluation and safety",
|
||||
container_image=None,
|
||||
template_path=Path(__file__).parent / "doc_template.md",
|
||||
providers=providers,
|
||||
available_models_by_provider=available_models,
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [inference_provider],
|
||||
"datasetio": [datasetio_provider],
|
||||
"eval": [eval_provider],
|
||||
},
|
||||
default_models=default_models,
|
||||
default_tool_groups=default_tool_groups,
|
||||
),
|
||||
"run-with-safety.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [
|
||||
inference_provider,
|
||||
safety_provider,
|
||||
],
|
||||
"eval": [eval_provider],
|
||||
},
|
||||
default_models=[inference_model, safety_model],
|
||||
default_shields=[ShieldInput(shield_id="${env.SAFETY_MODEL}", provider_id="nvidia")],
|
||||
default_tool_groups=default_tool_groups,
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"NVIDIA_API_KEY": (
|
||||
"",
|
||||
"NVIDIA API Key",
|
||||
),
|
||||
"NVIDIA_APPEND_API_VERSION": (
|
||||
"True",
|
||||
"Whether to append the API version to the base_url",
|
||||
),
|
||||
## Nemo Customizer related variables
|
||||
"NVIDIA_DATASET_NAMESPACE": (
|
||||
"default",
|
||||
"NVIDIA Dataset Namespace",
|
||||
),
|
||||
"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",
|
||||
),
|
||||
"NVIDIA_GUARDRAILS_CONFIG_ID": (
|
||||
"self-check",
|
||||
"NVIDIA Guardrail Configuration ID",
|
||||
),
|
||||
"NVIDIA_EVALUATOR_URL": (
|
||||
"http://0.0.0.0:7331",
|
||||
"URL for the NeMo Evaluator 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",
|
||||
),
|
||||
},
|
||||
)
|
||||
Loading…
Add table
Add a link
Reference in a new issue