minor: limit the range of vllm versions (#2350)

python/pyproject.toml

@@ -23,7 +23,7 @@ runtime_common = ["aiohttp", "decord", "fastapi",
     "psutil", "pydantic", "python-multipart",
     "pyzmq>=25.1.2", "torchao", "uvicorn", "uvloop",
     "xgrammar>=0.1.4"]
-srt = ["sglang[runtime_common]", "torch", "vllm>=0.6.3.post1", "cuda-python", "flashinfer>=0.1.6"]
+srt = ["sglang[runtime_common]", "torch", "vllm>=0.6.3.post1,<=0.6.4.post1", "cuda-python", "flashinfer>=0.1.6"]
 
 # HIP (Heterogeneous-computing Interface for Portability) for AMD
 # => base docker rocm/vllm-dev:20241022, not from public vllm whl

python/sglang/__init__.py

@@ -66,7 +66,7 @@ from sglang.version import __version__
 
 __all__ += ["__version__"]
 
-# SGL Backends
+# SGLang Backends
 from sglang.lang.backend.runtime_endpoint import RuntimeEndpoint
 from sglang.utils import LazyImport