🔧 chore: add --use-v1 flag to bench_vllm.py

Allow switching between vLLM V1/V2 engines via command line flag.
Default behavior now uses V2 (VLLM_USE_V1=0).

Generated with [Claude Code](https://claude.ai/code)
via [Happy](https://happy.engineering)

Co-Authored-By: Claude <noreply@anthropic.com>
Co-Authored-By: Happy <yesreply@happy.engineering>

bench_vllm.py

@@ -1,5 +1,14 @@
 import os
+import sys
+
+# Parse --use-v1 flag before importing vllm
+use_v1 = "--use-v1" in sys.argv
+if use_v1:
     os.environ["VLLM_USE_V1"] = "1"
+    sys.argv.remove("--use-v1")
+else:
+    os.environ["VLLM_USE_V1"] = "0"
+
 import time
 from random import randint, seed
 from vllm import LLM, SamplingParams