relocate nvidia-modelopt dependency to srt

python/pyproject.toml

@@ -17,13 +17,13 @@ dependencies = ["requests", "tqdm", "numpy", "IPython", "setproctitle"]
 
 [project.optional-dependencies]
 runtime_common = ["aiohttp", "decord", "fastapi",
-    "hf_transfer", "huggingface_hub", "interegular", "nvidia-modelopt", "modelscope",
+    "hf_transfer", "huggingface_hub", "interegular", "modelscope",
     "orjson", "outlines>=0.0.44,<0.1.0",
     "packaging", "pillow", "prometheus-client>=0.20.0",
     "psutil", "pydantic", "python-multipart",
     "pyzmq>=25.1.2", "torchao>=0.7.0", "uvicorn", "uvloop",
     "xgrammar>=0.1.6"]
-srt = ["sglang[runtime_common]", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1", "cuda-python", "flashinfer==0.1.6", "sgl-kernel>=0.0.2.post10"]
+srt = ["sglang[runtime_common]", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1", "cuda-python", "flashinfer==0.1.6", "sgl-kernel>=0.0.2.post10", "nvidia-modelopt"]
 
 # HIP (Heterogeneous-computing Interface for Portability) for AMD
 # => base docker rocm/vllm-dev:20241022, not from public vllm whl