Add pydocstyle to the ruff rules (#52136)

Signed-off-by: Harry Mellor <19981378+hmellor@users.noreply.github.com>
Signed-off-by: Harry Mellor <hej.mellor@gmail.com>
Co-authored-by: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Harry Mellor
2026-09-16 16:44:29 +00:00
committed by GitHub
co-authored by Claude Opus 5
parent 804e5377aa
commit 8c1557a79c
2002 changed files with 15024 additions and 14269 deletions
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""
This file demonstrates the example usage of CPU offloading
"""This file demonstrates the example usage of CPU offloading
with LMCache in vLLM v1.
Note that `lmcache` is needed to run this example.
@@ -14,9 +14,7 @@ from fastapi.responses import StreamingResponse
@asynccontextmanager
async def lifespan(app: FastAPI):
"""
Lifespan context manager to handle startup and shutdown events.
"""
"""Lifespan context manager to handle startup and shutdown events."""
# Startup: Initialize clients
prefiller_base_url = (
f"http://{global_args.prefiller_host}:{global_args.prefiller_port}/v1"
@@ -106,9 +104,7 @@ app.state.decode_client = None
async def send_request_to_service(
client: httpx.AsyncClient, endpoint: str, req_data: dict
):
"""
Send a request to a service using a persistent client.
"""
"""Send a request to a service using a persistent client."""
req_data = req_data.copy()
req_data["max_tokens"] = 1
if "max_completion_tokens" in req_data:
@@ -128,9 +124,7 @@ async def send_request_to_service(
async def stream_service_response(
client: httpx.AsyncClient, endpoint: str, req_data: dict
):
"""
Asynchronously stream the response from a service using a persistent client.
"""
"""Asynchronously stream the response from a service using a persistent client."""
headers = {"Authorization": f"Bearer {os.environ.get('OPENAI_API_KEY')}"}
async with client.stream(
"POST", endpoint, json=req_data, headers=headers
@@ -1,7 +1,6 @@
# SPDX-License-Identifier: Apache-2.0
# SPDX-FileCopyrightText: Copyright contributors to the vLLM project
"""
This file demonstrates the example usage of remote KV cache sharing
"""This file demonstrates the example usage of remote KV cache sharing
with LMCache.
We will launch 2 vllm instances, and launch an additional LMCache server.
KV cache is transferred in the following manner: