From 104c66f0992dd48d7825f8331beeed398e468a2a Mon Sep 17 00:00:00 2001 From: Ashwin Bharambe Date: Tue, 26 Aug 2025 12:28:48 -0700 Subject: [PATCH] sentence transformers had a subtle dep on torchao --- docs/source/providers/post_training/index.md | 1 - llama_stack/providers/registry/inference.py | 3 ++- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/docs/source/providers/post_training/index.md b/docs/source/providers/post_training/index.md index 5ada6f9aa..e69f2a45a 100644 --- a/docs/source/providers/post_training/index.md +++ b/docs/source/providers/post_training/index.md @@ -9,7 +9,6 @@ This section contains documentation for all available providers for the **post_t ```{toctree} :maxdepth: 1 -inline_huggingface-cpu inline_huggingface-gpu inline_torchtune-cpu inline_torchtune-gpu diff --git a/llama_stack/providers/registry/inference.py b/llama_stack/providers/registry/inference.py index 1801cdcad..0efcc3cee 100644 --- a/llama_stack/providers/registry/inference.py +++ b/llama_stack/providers/registry/inference.py @@ -40,8 +40,9 @@ def available_providers() -> list[ProviderSpec]: InlineProviderSpec( api=Api.inference, provider_type="inline::sentence-transformers", + # CrossEncoder depends on torchao.quantization pip_packages=[ - "torch torchvision --index-url https://download.pytorch.org/whl/cpu", + "torch torchvision torchao --index-url https://download.pytorch.org/whl/cpu", "sentence-transformers --no-deps", ], module="llama_stack.providers.inline.inference.sentence_transformers",