phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-27 18:50:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Split off meta-reference-quantized provider

Browse source
This commit is contained in:
Ashwin Bharambe 2024-10-10 15:54:08 -07:00
parent 7ff5800dea
commit 1ff0476002
10 changed files with 54 additions and 58 deletions
Download patch file Download diff file Expand all files Collapse all files

17
llama_stack/providers/registry/inference.py
View file

@ -14,6 +14,21 @@ def available_providers() -> List[ProviderSpec]:
InlineProviderSpec(
api=Api.inference,
provider_type="meta-reference",
pip_packages=[
"accelerate",
"blobfile",
"fairscale",
"torch",
"torchvision",
"transformers",
"zmq",
],
module="llama_stack.providers.impls.meta_reference.inference",
config_class="llama_stack.providers.impls.meta_reference.inference.MetaReferenceInferenceConfig",
),
InlineProviderSpec(
api=Api.inference,
provider_type="meta-reference-quantized",
pip_packages=[
"accelerate",
"blobfile",
@ -25,7 +40,7 @@ def available_providers() -> List[ProviderSpec]:
"zmq",
],
module="llama_stack.providers.impls.meta_reference.inference",
config_class="llama_stack.providers.impls.meta_reference.inference.MetaReferenceImplConfig",
config_class="llama_stack.providers.impls.meta_reference.inference.MetaReferenceQuantizedInferenceConfig",
),
remote_provider_spec(
api=Api.inference,