phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-23 16:41:49 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(vllm): periodically refresh models

Browse source
This commit is contained in:
Ashwin Bharambe 2025-07-18 15:33:33 -07:00
parent 68a2dfbad7
commit 1bf710bec0
6 changed files with 95 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

10
llama_stack/providers/remote/inference/vllm/config.py
View file

@ -29,6 +29,14 @@ class VLLMInferenceAdapterConfig(BaseModel):
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
@ -46,7 +54,7 @@ class VLLMInferenceAdapterConfig(BaseModel):
@classmethod
def sample_run_config(
cls,
url: str = "${env.VLLM_URL}",
url: str = "${env.VLLM_URL:=}",
**kwargs,
):
return {