phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-05 04:17:32 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(distro): fork off a starter-gpu distribution (#3240)

Browse source 
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.
This commit is contained in:
Ashwin Bharambe 2025-08-22 15:47:15 -07:00 • committed by GitHub
parent 3b9278f254
commit 7519b73fcc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
15 changed files with 522 additions and 31 deletions
Download patch file Download diff file Expand all files Collapse all files

22
llama_stack/distributions/starter-gpu/starter_gpu.py Normal file
View file

@ -0,0 +1,22 @@
# 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