llama-stack-mirror/llama_stack/providers/adapters/inference/vllm/config.py
Ashwin Bharambe b10e9f46bb
Enable remote::vllm (#384)
* Enable remote::vllm

* Kill the giant list of hard coded models
2024-11-06 14:42:44 -08:00

26 lines
738 B
Python

# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
#
# This source code is licensed under the terms described in the LICENSE file in
# the root directory of this source tree.
from typing import Optional
from llama_models.schema_utils import json_schema_type
from pydantic import BaseModel, Field
@json_schema_type
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="fake",
description="The API token",
)