From 1d855461d55b0aec705cdc1a83324a5453838401 Mon Sep 17 00:00:00 2001 From: Ashwin Bharambe Date: Fri, 11 Apr 2025 16:21:21 -0700 Subject: [PATCH] kill batch inference registry --- .../providers/registry/batch_inference.py | 39 ------------------- 1 file changed, 39 deletions(-) delete mode 100644 llama_stack/providers/registry/batch_inference.py diff --git a/llama_stack/providers/registry/batch_inference.py b/llama_stack/providers/registry/batch_inference.py deleted file mode 100644 index 07b2167d6..000000000 --- a/llama_stack/providers/registry/batch_inference.py +++ /dev/null @@ -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", - ), - ]