phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-29 03:14:19 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Enable remote::vllm (#384)

Browse source 
* Enable remote::vllm

* Kill the giant list of hard coded models
This commit is contained in:
Ashwin Bharambe 2024-11-06 14:42:44 -08:00 • committed by GitHub
parent 093c9f1987
commit b10e9f46bb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 80 additions and 53 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/providers/adapters/inference/vllm/config.py
View file

@ -11,12 +11,16 @@ from pydantic import BaseModel, Field
@json_schema_type
class VLLMImplConfig(BaseModel):
class VLLMInferenceAdapterConfig(BaseModel):
url: Optional[str] = Field(
default=None,
description="The URL for the vLLM model serving endpoint",
)
max_tokens: int = Field(
default=4096,
description="Maximum number of tokens to generate.",
)
api_token: Optional[str] = Field(
default=None,
default="fake",
description="The API token",
)