Update ray to 2.50.0 to for prepackaged click version ban, install additional packages for RDMA support, add additional env vars for RDMA, remove UCX

Author: XkunW

Dockerfile

@@ -35,17 +35,21 @@ RUN wget https://bootstrap.pypa.io/get-pip.py && \
     rm get-pip.py && \
     python3.10 -m pip install --upgrade pip setuptools wheel uv
 
-# Install Infiniband/RDMA support
+# Install RDMA support
 RUN apt-get update && apt-get install -y \
     libibverbs1 libibverbs-dev ibverbs-utils \
     librdmacm1 librdmacm-dev rdmacm-utils \
+    rdma-core ibverbs-providers infiniband-diags perftest \
     && rm -rf /var/lib/apt/lists/*
 
 # Set up RDMA environment (these will persist in the final container)
 ENV LD_LIBRARY_PATH="/usr/lib/x86_64-linux-gnu:$LD_LIBRARY_PATH"
-ENV UCX_NET_DEVICES=all
 ENV NCCL_IB_DISABLE=0
-ENV NCCL_SOCKET_IFNAME=ib0
+ENV NCCL_SOCKET_IFNAME="^lo,docker0"
+ENV NCCL_NET_GDR_LEVEL=PHB
+ENV NCCL_IB_TIMEOUT=22
+ENV NCCL_IB_RETRY_CNT=7
+ENV NCCL_DEBUG=WARN
 
 # Set up project
 WORKDIR /vec-inf
@@ -59,8 +63,5 @@ RUN apt-get update && apt-get install -y --allow-change-held-packages\
     libnccl2 libnccl-dev \
     && rm -rf /var/lib/apt/lists/*
 
-# Final configuration
-ENV NCCL_DEBUG=INFO
-
 # Set the default command to start an interactive shell
 CMD ["bash"]

pyproject.toml

@@ -8,7 +8,7 @@ license = "MIT"
 requires-python = ">=3.10"
 dependencies = [
     "requests>=2.31.0",
-    "click>=8.1.0,!=8.3.0",
+    "click>=8.1.0",
     "rich>=13.7.0",
     "pydantic>=2.10.6",
     "pyyaml>=6.0.2",
@@ -42,7 +42,7 @@ dev = [
     "xgrammar>=0.1.11",
     "torch>=2.7.0",
     "vllm>=0.10.0",
-    "ray>=2.40.0,<2.46.0",
+    "ray>=2.50.0",
     "cupy-cuda12x==12.1.0"
 ]