mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-07-21 03:59:42 +00:00
199f859eec
Just like #2805 but for vLLM. We also make VLLM_URL env variable optional (not required) -- if not specified, the provider silently sits idle and yells eventually if someone tries to call a completion on it. This is done so as to allow this provider to be present in the `starter` distribution. ## Test Plan Set up vLLM, copy the starter template and set `{ refresh_models: true, refresh_models_interval: 10 }` for the vllm provider and then run: ``` ENABLE_VLLM=vllm VLLM_URL=http://localhost:8000/v1 \ uv run llama stack run --image-type venv /tmp/starter.yaml ``` Verify that `llama-stack-client models list` brings up the model correctly from vLLM.
65 lines
2 KiB
Python
65 lines
2 KiB
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 pathlib import Path
|
|
|
|
from pydantic import BaseModel, Field, field_validator
|
|
|
|
from llama_stack.schema_utils import json_schema_type
|
|
|
|
|
|
@json_schema_type
|
|
class VLLMInferenceAdapterConfig(BaseModel):
|
|
url: str | None = 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: str | None = Field(
|
|
default="fake",
|
|
description="The API token",
|
|
)
|
|
tls_verify: bool | str = Field(
|
|
default=True,
|
|
description="Whether to verify TLS certificates. Can be a boolean or a path to a CA certificate file.",
|
|
)
|
|
refresh_models: bool = Field(
|
|
default=False,
|
|
description="Whether to refresh models periodically",
|
|
)
|
|
refresh_models_interval: int = Field(
|
|
default=300,
|
|
description="Interval in seconds to refresh models",
|
|
)
|
|
|
|
@field_validator("tls_verify")
|
|
@classmethod
|
|
def validate_tls_verify(cls, v):
|
|
if isinstance(v, str):
|
|
# Otherwise, treat it as a cert path
|
|
cert_path = Path(v).expanduser().resolve()
|
|
if not cert_path.exists():
|
|
raise ValueError(f"TLS certificate file does not exist: {v}")
|
|
if not cert_path.is_file():
|
|
raise ValueError(f"TLS certificate path is not a file: {v}")
|
|
return v
|
|
return v
|
|
|
|
@classmethod
|
|
def sample_run_config(
|
|
cls,
|
|
url: str = "${env.VLLM_URL:=}",
|
|
**kwargs,
|
|
):
|
|
return {
|
|
"url": url,
|
|
"max_tokens": "${env.VLLM_MAX_TOKENS:=4096}",
|
|
"api_token": "${env.VLLM_API_TOKEN:=fake}",
|
|
"tls_verify": "${env.VLLM_TLS_VERIFY:=true}",
|
|
}
|