fix: ruff errors

Author: AlonKellner-Jounce

tests/e2e/README.md

@@ -2,4 +2,4 @@
 The E2E tests in GuideLLM use the [vLLM simulator by llm-d](https://llm-d.ai/docs/architecture/Components/inf-simulator), to run them run the following command:
 ```shell
 docker build . -f tests/e2e/vllm-sim.Dockerfile -o type=local,dest=./
-```
+```

tests/e2e/test_basic.py

@@ -40,7 +40,7 @@ def test_basic_report(server: VllmSimServer):
   --data "prompt_tokens=256,output_tokens=128" \
   --output-path {report_path}
               """
-    logger.info(f"Client command: {command}") # guidellm benchmark   --target "http://127.0.0.1:8000"   --rate-type constant   --rate 5   --max-seconds 5   --data "prompt_tokens=256,output_tokens=128"
+    logger.info(f"Client command: {command}")
     os.system(command)  # noqa: S605
 
     assert report_path.exists()

tests/e2e/test_interrupted.py

@@ -1,11 +1,9 @@
 # test_server_interaction.py
 
 import json
-import os
-from pathlib import Path
 import subprocess
 import time
-
+from pathlib import Path
 
 import pytest
 from loguru import logger
@@ -44,7 +42,7 @@ def test_interrupted_report(server: VllmSimServer):
   --data "prompt_tokens=256,output_tokens=128" \
   --output-path {report_path}
               """
-    logger.info(f"Client command: {command}") # guidellm benchmark   --target "http://127.0.0.1:8000"   --rate-type constant   --rate 5   --max-seconds 5   --data "prompt_tokens=256,output_tokens=128"
+    logger.info(f"Client command: {command}")
     process = subprocess.Popen(["/bin/bash", "-c", command],  # noqa: S603
             stdout=subprocess.PIPE,
             stderr=subprocess.PIPE,

tests/e2e/vllm_sim_server.py

@@ -1,5 +1,6 @@
 import subprocess
 import time
+from typing import Optional
 
 import pytest
 import requests
@@ -16,15 +17,15 @@ def __init__(
         self,
         port: int,
         model: str,
-        lora: list[str] | None = None,
-        mode: str | None = None,
-        echo: bool | None = None,
-        random: bool | None = None,
-        time_to_first_token: float | None = None,
-        inter_token_latency: float | None = None,
-        max_loras: int | None = None,
-        max_cpu_loras: int | None = None,
-        max_running_requests: int | None = None,
+        lora: Optional[list[str]] = None,
+        mode: Optional[str] = None,
+        echo: Optional[bool] = None,
+        random: Optional[bool] = None,
+        time_to_first_token: Optional[float] = None,
+        inter_token_latency: Optional[float] = None,
+        max_loras: Optional[int] = None,
+        max_cpu_loras: Optional[int] = None,
+        max_running_requests: Optional[int] = None,
     ):
         self.port = port
         self.model = model
@@ -40,13 +41,10 @@ def __init__(
         self.server_url = f"http://127.0.0.1:{self.port}"
         self.health_url = f"{self.server_url}/health"
         self.app_script = "./bin/llm-d-inference-sim"
-        self.process = None
+        self.process: Optional[subprocess.Popen] = None
 
     def get_cli_parameters(self) -> list[str]:
-        parameters = [
-            "--port", f"{self.port}",
-            "--model", self.model
-        ]
+        parameters = ["--port", f"{self.port}", "--model", self.model]
         if self.lora is not None:
             parameters.extend(["--lora", ",".join(self.lora)])
         if self.mode is not None:
@@ -64,19 +62,20 @@ def get_cli_parameters(self) -> list[str]:
         if self.max_cpu_loras is not None:
             parameters.extend(["--max-cpu-loras", f"{self.max_cpu_loras}"])
         if self.max_running_requests is not None:
-            parameters.extend(["--max-running-requests", f"{self.max_running_requests}"])
+            parameters.extend(
+                ["--max-running-requests", f"{self.max_running_requests}"]
+            )
         return parameters
 
     def start(self):
         """
         Starts the server process and waits for it to become healthy.
         """
 
-        logger.info(f"Starting server on {self.server_url}"
-                    f" using {self.app_script}...")
+        logger.info(f"Starting server on {self.server_url} using {self.app_script}...")
         cli_parameters = self.get_cli_parameters()
         command = " ".join([self.app_script, *cli_parameters])
-        logger.info(f"Server command: {command}") # ./bin/llm-d-inference-sim --model databricks/dolly-v2-12b --port 8000
+        logger.info(f"Server command: {command}")
         self.process = subprocess.Popen(  # noqa: S603
             [self.app_script, *cli_parameters],
             stdout=subprocess.PIPE,