phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 19:02:37 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

sentence transformers had a subtle dep on torchao

Browse source
This commit is contained in:
Ashwin Bharambe 2025-08-26 12:28:48 -07:00
parent bd28427d61
commit 104c66f099
2 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

1
docs/source/providers/post_training/index.md
View file

@ -9,7 +9,6 @@ This section contains documentation for all available providers for the **post_t
```{toctree} ```{toctree}
:maxdepth: 1 :maxdepth: 1
inline_huggingface-cpu
inline_huggingface-gpu inline_huggingface-gpu
inline_torchtune-cpu inline_torchtune-cpu
inline_torchtune-gpu inline_torchtune-gpu

3
llama_stack/providers/registry/inference.py
View file

@ -40,8 +40,9 @@ def available_providers() -> list[ProviderSpec]:
InlineProviderSpec( InlineProviderSpec(
api=Api.inference, api=Api.inference,
provider_type="inline::sentence-transformers", provider_type="inline::sentence-transformers",
# CrossEncoder depends on torchao.quantization
pip_packages=[ 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", "sentence-transformers --no-deps",
], ],
module="llama_stack.providers.inline.inference.sentence_transformers", module="llama_stack.providers.inline.inference.sentence_transformers",