phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-03 01:03:59 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

kill batch inference registry

Browse source
This commit is contained in:
Ashwin Bharambe 2025-04-11 16:21:21 -07:00
parent 73d927850e
commit 1d855461d5
1 changed files with 0 additions and 39 deletions
Download patch file Download diff file Expand all files Collapse all files

39
llama_stack/providers/registry/batch_inference.py
View file

@ -1,39 +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 typing import List
from llama_stack.providers.datatypes import (
Api,
InlineProviderSpec,
ProviderSpec,
)
META_REFERENCE_DEPS = [
"accelerate",
"blobfile",
"fairscale",
"torch",
"torchvision",
"transformers",
"zmq",
"lm-format-enforcer",
"sentence-transformers",
"torchao==0.5.0",
"fbgemm-gpu-genai==1.1.2",
]
def available_providers() -> List[ProviderSpec]:
return [
InlineProviderSpec(
api=Api.inference,
provider_type="inline::meta-reference",
pip_packages=META_REFERENCE_DEPS,
module="llama_stack.providers.inline.batch_inference.meta_reference",
config_class="llama_stack.providers.inline.batch_inference.meta_reference.MetaReferenceInferenceConfig",
),
]