mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-17 11:22:35 +00:00
Update Fireworks + Togther documentation
This commit is contained in:
parent
1ecaf2cb3c
commit
a562668dcd
27 changed files with 879 additions and 445 deletions
60
llama_stack/templates/fireworks/fireworks.py
Normal file
60
llama_stack/templates/fireworks/fireworks.py
Normal file
|
|
@ -0,0 +1,60 @@
|
|||
# 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
|
||||
from llama_stack.providers.remote.inference.fireworks import FireworksImplConfig
|
||||
from llama_stack.providers.remote.inference.fireworks.fireworks import MODEL_ALIASES
|
||||
|
||||
from llama_stack.templates.template import DistributionTemplate, RunConfigSettings
|
||||
|
||||
|
||||
def get_distribution_template() -> DistributionTemplate:
|
||||
providers = {
|
||||
"inference": ["remote::fireworks"],
|
||||
"memory": ["inline::faiss", "remote::chromadb", "remote::pgvector"],
|
||||
"safety": ["inline::llama-guard"],
|
||||
"agents": ["inline::meta-reference"],
|
||||
"telemetry": ["inline::meta-reference"],
|
||||
}
|
||||
|
||||
inference_provider = Provider(
|
||||
provider_id="fireworks",
|
||||
provider_type="remote::fireworks",
|
||||
config=FireworksImplConfig.sample_run_config(),
|
||||
)
|
||||
|
||||
default_models = [ModelInput(model_id=m.provider_model_id) for m in MODEL_ALIASES]
|
||||
|
||||
return DistributionTemplate(
|
||||
name="fireworks",
|
||||
distro_type="self_hosted",
|
||||
description="Use Fireworks.AI for running LLM inference",
|
||||
docker_image=None,
|
||||
template_path=Path(__file__).parent / "doc_template.md",
|
||||
providers=providers,
|
||||
default_models=default_models,
|
||||
run_configs={
|
||||
"run.yaml": RunConfigSettings(
|
||||
provider_overrides={
|
||||
"inference": [inference_provider],
|
||||
},
|
||||
default_models=default_models,
|
||||
default_shields=[ShieldInput(shield_id="meta-llama/Llama-Guard-3-8B")],
|
||||
),
|
||||
},
|
||||
run_config_env_vars={
|
||||
"LLAMASTACK_PORT": (
|
||||
"5001",
|
||||
"Port for the Llama Stack distribution server",
|
||||
),
|
||||
"FIREWORKS_API_KEY": (
|
||||
"",
|
||||
"Fireworks.AI API Key",
|
||||
),
|
||||
},
|
||||
)
|
||||
Loading…
Add table
Add a link
Reference in a new issue