phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-29 10:02:20 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into add-watsonx-inference-adapter

Browse source
This commit is contained in:
Sajikumar JS 2025-04-06 16:28:39 +05:30
commit 8cf8bd35f8
141 changed files with 206076 additions and 6917 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/registry/inference.py
View file

@ -39,13 +39,7 @@ def available_providers() -> List[ProviderSpec]:
InlineProviderSpec(
api=Api.inference,
provider_type="inline::meta-reference-quantized",
pip_packages=(
META_REFERENCE_DEPS
+ [
"fbgemm-gpu",
"torchao==0.5.0",
]
),
pip_packages=META_REFERENCE_DEPS + ["fbgemm-gpu", "torchao==0.5.0"],
module="llama_stack.providers.inline.inference.meta_reference",
config_class="llama_stack.providers.inline.inference.meta_reference.MetaReferenceQuantizedInferenceConfig",
),