chore: bump v0.2.14 (#1155)

README.md

@@ -56,7 +56,7 @@ pip install flashinfer -i https://flashinfer.ai/whl/cu121/torch2.4/
 ### Method 2: From source
 ```
 # Use the last release branch
-git clone -b v0.2.13 https://github.com/sgl-project/sglang.git
+git clone -b v0.2.14 https://github.com/sgl-project/sglang.git
 cd sglang
 
 pip install --upgrade pip

python/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "sglang"
-version = "0.2.13"
+version = "0.2.14"
 description = "SGLang is yet another fast serving framework for large language models and vision language models."
 readme = "README.md"
 requires-python = ">=3.8"
@@ -23,7 +23,7 @@ dependencies = [
 srt = ["aiohttp", "decord", "fastapi", "hf_transfer", "huggingface_hub", "interegular",
        "packaging", "pillow", "psutil", "pydantic", "python-multipart",
        "torch", "uvicorn", "uvloop", "zmq",
-       "vllm==0.5.4", "outlines>=0.0.44"]
+       "vllm==0.5.5", "outlines>=0.0.44"]
 openai = ["openai>=1.0", "tiktoken"]
 anthropic = ["anthropic>=0.20.0"]
 litellm = ["litellm>=1.0.0"]

python/sglang/srt/model_executor/model_runner.py

@@ -191,12 +191,11 @@ def load_model(self):
 
         self.model = get_model(
             model_config=self.vllm_model_config,
-            device_config=self.device_config,
             load_config=self.load_config,
-            lora_config=None,
-            multimodal_config=None,
+            device_config=self.device_config,
             parallel_config=None,
             scheduler_config=None,
+            lora_config=None,
             cache_config=None,
         )
         self.sliding_window_size = (
@@ -627,4 +626,4 @@ def load_model_cls_srt(model_arch: str) -> Optional[Type[nn.Module]]:
 
 
 # Monkey patch model loader
-setattr(ModelRegistry, "load_model_cls", load_model_cls_srt)
+setattr(ModelRegistry, "_try_load_model_cls", load_model_cls_srt)

python/sglang/version.py

@@ -1 +1 @@
-__version__ = "0.2.13"
+__version__ = "0.2.14"