mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 20:14:13 +00:00
7519b73fcc
The starter distribution added post-training which added torch dependencies which pulls in all the nvidia CUDA libraries. This made our starter container very big. We have worked hard to keep the starter container small so it serves its purpose as a starter. This PR tries to get it back to its size by forking off duplicate "-gpu" providers for post-training. These forked providers are then used for a new `starter-gpu` distribution which can pull in all dependencies.
22 lines
838 B
Python
22 lines
838 B
Python
# 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 llama_stack.distributions.template import BuildProvider, DistributionTemplate
|
|
|
|
from ..starter.starter import get_distribution_template as get_starter_distribution_template
|
|
|
|
|
|
def get_distribution_template() -> DistributionTemplate:
|
|
template = get_starter_distribution_template()
|
|
name = "starter-gpu"
|
|
template.name = name
|
|
template.description = "Quick start template for running Llama Stack with several popular providers. This distribution is intended for GPU-enabled environments."
|
|
|
|
template.providers["post_training"] = [
|
|
BuildProvider(provider_type="inline::torchtune-gpu"),
|
|
]
|
|
return template
|