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

migrate model to Resource and new registration signature (#410)

Browse source 
* resource oriented object design for models

* add back llama_model field

* working tests

* register singature fix

* address feedback

---------

Co-authored-by: Dinesh Yeduguru <dineshyv@fb.com>
This commit is contained in:
Dinesh Yeduguru 2024-11-08 16:12:57 -08:00 • committed by GitHub
parent bd0622ef10
commit ec644d3418
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
17 changed files with 99 additions and 90 deletions
Download patch file Download diff file Expand all files Collapse all files

12
llama_stack/providers/inline/inference/vllm/vllm.py
View file

@ -20,7 +20,7 @@ from vllm.sampling_params import SamplingParams as VLLMSamplingParams
from llama_stack.apis.inference import * # noqa: F403
from llama_stack.providers.datatypes import ModelDef, ModelsProtocolPrivate
from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate
from llama_stack.providers.utils.inference.openai_compat import (
OpenAICompatCompletionChoice,
OpenAICompatCompletionResponse,
@ -83,19 +83,11 @@ class VLLMInferenceImpl(Inference, ModelsProtocolPrivate):
if self.engine:
self.engine.shutdown_background_loop()
async def register_model(self, model: ModelDef) -> None:
async def register_model(self, model: Model) -> None:
raise ValueError(
"You cannot dynamically add a model to a running vllm instance"
)
async def list_models(self) -> List[ModelDef]:
return [
ModelDef(
identifier=self.config.model,
llama_model=self.config.model,
)
]
def _sampling_params(self, sampling_params: SamplingParams) -> VLLMSamplingParams:
if sampling_params is None:
return VLLMSamplingParams(max_tokens=self.config.max_tokens)