Clean up import vllm in quantization/__init__.py (#4834)

python/pyproject.toml

@@ -17,6 +17,7 @@ dependencies = ["aiohttp", "requests", "tqdm", "numpy", "IPython", "setproctitle
 
 [project.optional-dependencies]
 runtime_common = [
+    "compressed-tensors",
     "datasets",
     "decord",
     "fastapi",
@@ -56,7 +57,12 @@ srt = [
 
 # HIP (Heterogeneous-computing Interface for Portability) for AMD
 # => base docker rocm/vllm-dev:20250114, not from public vllm whl
-srt_hip = ["sglang[runtime_common]", "torch", "vllm==0.6.7.dev2", "outlines==0.1.11"]
+srt_hip = [
+    "sglang[runtime_common]",
+    "torch",
+    "vllm==0.6.7.dev2",
+    "outlines==0.1.11"
+]
 
 # xpu is not enabled in public vllm and torch whl,
 # need to follow https://docs.vllm.ai/en/latest/getting_started/xpu-installation.htmlinstall vllm