phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-17 22:47:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

temp commit

Browse source
This commit is contained in:
Botao Chen 2024-12-16 19:04:47 -08:00
parent b2dbb5e3fe
commit 30f6eb282f
7 changed files with 16 additions and 15 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/inline/inference/meta_reference/__init__.py
View file

@ -15,9 +15,6 @@ async def get_provider_impl(
):
from .inference import MetaReferenceInferenceImpl
print("get_provider_impl")
impl = MetaReferenceInferenceImpl(config)
print("after MetaReferenceInferenceImpl")
return impl

2
llama_stack/providers/inline/inference/meta_reference/inference.py
View file

@ -94,7 +94,6 @@ class MetaReferenceInferenceImpl(
],
)
model = await self.model_registry_helper.register_model(model)
print("model type", type(model))
if model.model_type == ModelType.embedding:
self._load_sentence_transformer_model(model.provider_resource_id)
@ -304,7 +303,6 @@ class MetaReferenceInferenceImpl(
if self.config.create_distributed_process_group:
async with SEMAPHORE:
print("after SEMAPHORE")
return impl()
else:
return impl()

2
llama_stack/providers/inline/inference/meta_reference/model_parallel.py
View file

@ -58,7 +58,6 @@ class LlamaModelParallelGenerator:
config: MetaReferenceInferenceConfig,
model_id: str,
):
print("LlamaModelParallelGenerator init")
self.config = config
self.model_id = model_id
self.model = resolve_model(model_id)
@ -76,7 +75,6 @@ class LlamaModelParallelGenerator:
self.__exit__(None, None, None)
def __enter__(self):
print("enter LlamaModelParallelGenerator")
if self.config.model_parallel_size:
model_parallel_size = self.config.model_parallel_size
else: