phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-31 08:53:54 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: introduce llama4 support

Browse source
This commit is contained in:
Ashwin Bharambe 2025-04-05 09:39:05 -07:00
parent 23a99a4b22
commit 20cbcdf0d5
61 changed files with 205222 additions and 6439 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",
),