Merge code

Signed-off-by: Rafael Vasquez <[email protected]>

Dockerfile

@@ -163,7 +163,7 @@ RUN PYTHON_VERSION_STR=$(echo ${PYTHON_VERSION} | sed 's/\.//g') && \
 RUN echo 'tzdata tzdata/Areas select America' | debconf-set-selections \
     && echo 'tzdata tzdata/Zones/America select Los_Angeles' | debconf-set-selections \
     && apt-get update -y \
-    && apt-get install -y ccache software-properties-common git curl sudo vim python3-pip \
+    && apt-get install -y ccache software-properties-common git curl wget sudo vim python3-pip \
     && apt-get install -y ffmpeg libsm6 libxext6 libgl1 \
     && add-apt-repository ppa:deadsnakes/ppa \
     && apt-get update -y \

docs/source/getting_started/debugging.md

@@ -196,3 +196,4 @@ if __name__ == '__main__':
 ## Known Issues
 
 - In `v0.5.2`, `v0.5.3`, and `v0.5.3.post1`, there is a bug caused by [zmq](https://github.com/zeromq/pyzmq/issues/2000) , which can occasionally cause vLLM to hang depending on the machine configuration. The solution is to upgrade to the latest version of `vllm` to include the [fix](https://github.com/vllm-project/vllm/pull/6759).
+- To circumvent a NCCL [bug](https://github.com/NVIDIA/nccl/issues/1234) , all vLLM processes will set an environment variable ``NCCL_CUMEM_ENABLE=0`` to disable NCCL's ``cuMem`` allocator. It does not affect performance but only gives memory benefits. When external processes want to set up a NCCL connection with vLLM's processes, they should also set this environment variable, otherwise, inconsistent environment setup will cause NCCL to hang or crash, as observed in the [RLHF integration](https://github.com/OpenRLHF/OpenRLHF/pull/604) and the [discussion](https://github.com/vllm-project/vllm/issues/5723#issuecomment-2554389656) .

requirements-cuda.txt

@@ -2,7 +2,7 @@
 -r requirements-common.txt
 
 # Dependencies for NVIDIA GPUs
-ray >= 2.9
+ray[default] >= 2.9
 nvidia-ml-py >= 12.560.30 # for pynvml package
 torch == 2.5.1
 # These must be updated alongside torch

vllm/entrypoints/openai/protocol.py

@@ -46,7 +46,15 @@ class OpenAIBaseModel(BaseModel):
     @classmethod
     def __log_extra_fields__(cls, data):
         if isinstance(data, dict):
-            extra_fields = data.keys() - cls.model_fields.keys()
+            # Get all class field names and their potential aliases
+            field_names = set()
+            for field_name, field in cls.model_fields.items():
+                field_names.add(field_name)
+                if hasattr(field, 'alias') and field.alias:
+                    field_names.add(field.alias)
+
+            # Compare against both field names and aliases
+            extra_fields = data.keys() - field_names
             if extra_fields:
                 logger.warning(
                     "The following fields were present in the request "