phoenix-oss/llama-stack
1
0
Fork 0
forked from phoenix-oss/llama-stack-mirror
Code Pull requests Releases Packages 2 Activity Actions

ModelAlias -> ProviderModelEntry

Browse source
This commit is contained in:
Ashwin Bharambe 2025-02-20 14:02:36 -08:00
parent 561295af76
commit 07ccf908f7
27 changed files with 132 additions and 132 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/remote/inference/vllm/vllm.py
View file

@ -38,7 +38,7 @@ from llama_stack.models.llama.sku_list import all_registered_models
from llama_stack.providers.datatypes import ModelsProtocolPrivate
from llama_stack.providers.utils.inference.model_registry import (
ModelRegistryHelper,
build_hf_repo_model_alias,
build_hf_repo_model_entry,
)
from llama_stack.providers.utils.inference.openai_compat import (
OpenAICompatCompletionResponse,
@ -62,9 +62,9 @@ from .config import VLLMInferenceAdapterConfig
log = logging.getLogger(__name__)
def build_hf_repo_model_aliases():
def build_hf_repo_model_entries():
return [
build_hf_repo_model_alias(
build_hf_repo_model_entry(
model.huggingface_repo,
model.descriptor(),
)
@ -204,7 +204,7 @@ async def _process_vllm_chat_completion_stream_response(
class VLLMInferenceAdapter(Inference, ModelsProtocolPrivate):
def __init__(self, config: VLLMInferenceAdapterConfig) -> None:
self.register_helper = ModelRegistryHelper(build_hf_repo_model_aliases())
self.register_helper = ModelRegistryHelper(build_hf_repo_model_entries())
self.config = config
self.client = None