phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-02 08:44:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Revert provider / inference config back to mainline

Browse source
This commit is contained in:
Connor Hack 2024-11-25 09:20:27 -08:00
parent 8d83759caf
commit bbea9bccf1
2 changed files with 3 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

4
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -36,8 +36,6 @@ class MetaReferenceInferenceImpl(Inference, ModelRegistryHelper, ModelsProtocolP
def __init__(self, config: MetaReferenceInferenceConfig) -> None:
self.config = config
model = resolve_model(config.model)
if model is None:
raise RuntimeError(f"Unknown model: {config.model}, Run `llama model list`")
ModelRegistryHelper.__init__(
self,
[
@ -47,6 +45,8 @@ class MetaReferenceInferenceImpl(Inference, ModelRegistryHelper, ModelsProtocolP
)
],
)
if model is None:
raise RuntimeError(f"Unknown model: {config.model}, Run `llama model list`")
self.model = model
# verify that the checkpoint actually is for this model lol

2
llama_stack/templates/meta-reference-gpu/meta_reference.py
View file

@ -81,7 +81,7 @@ def get_distribution_template() -> DistributionTemplate:
"Port for the Llama Stack distribution server",
),
"INFERENCE_MODEL": (
"meta-llama/Llama3.2-3B-Instruct",
"meta-llama/Llama-3.2-3B-Instruct",
"Inference model loaded into the Meta Reference server",
),
"INFERENCE_CHECKPOINT_DIR": (