diff --git a/Dockerfile b/Dockerfile
index 21cbe84..5555ebb 100644
--- a/Dockerfile
+++ b/Dockerfile
@@ -12,6 +12,7 @@ ENV VLLM_BASE_DIR=/workspace/vllm
 # 1. Install System Dependencies
 # Added 'git', 'wget', and 'python3-pip' as they are required for the script steps
 RUN apt-get update && apt-get install -y \
+    curl \
     cmake \
     build-essential \
     ninja-build \
@@ -36,8 +37,11 @@ ENV TORCH_CUDA_ARCH_LIST=12.1a
 ENV TRITON_PTXAS_PATH=/usr/local/cuda/bin/ptxas
 ENV TIKTOKEN_ENCODINGS_BASE=$VLLM_BASE_DIR/tiktoken_encodings
 
+# --- CACHE BUSTER ---
+# Change this argument to force a re-download of PyTorch/FlashInfer
+ARG CACHEBUST_DEPS=1
+
 # 4. Install Python Dependencies (Using pip instead of uv)
-#RUN python3 -m pip install --upgrade pip
 
 # Install PyTorch for CUDA 13.0
 RUN pip install torch torchvision torchaudio --index-url https://download.pytorch.org/whl/cu130
@@ -54,6 +58,11 @@ RUN pip install flashinfer-python --no-deps --index-url https://flashinfer.ai/wh
 # Install fast safetensors to improve loading speeds
 RUN pip install fastsafetensors>=0.1.10
 
+# --- VLLM SOURCE CACHE BUSTER ---
+# Change THIS argument to force a fresh git clone and rebuild of vLLM
+# without re-installing the dependencies above.
+ARG CACHEBUST_VLLM=1
+
 # 5. Clone and Build vLLM
 RUN git clone --recursive https://github.com/vllm-project/vllm.git
 WORKDIR $VLLM_BASE_DIR/vllm
@@ -63,6 +72,9 @@ RUN python3 use_existing_torch.py && \
     sed -i "/flashinfer/d" requirements/cuda.txt && \
     pip install -r requirements/build.txt
 
+# TEMPORARY - apply NVFP4 patch
+RUN curl -L https://patch-diff.githubusercontent.com/raw/vllm-project/vllm/pull/29242.diff | git apply
+
 # Final Build
 # Uses --no-build-isolation to respect the pre-installed Torch/FlashInfer
 # Changed -e (editable) to . (standard install) for better Docker portability
@@ -73,4 +85,4 @@ WORKDIR $VLLM_BASE_DIR
 
 # Copy clustering script
 COPY run-cluster-node.sh $VLLM_BASE_DIR/
-
+RUN chmod +x $VLLM_BASE_DIR/run-cluster-node.sh
diff --git a/README.md b/README.md
new file mode 100644
index 0000000..e3da041
--- /dev/null
+++ b/README.md
@@ -0,0 +1,118 @@
+# vLLM Ray Cluster Node Docker for DGX Spark
+
+This repository contains the Docker configuration and startup scripts to run a multi-node vLLM inference cluster using Ray. It supports InfiniBand/RDMA (NCCL) and custom environment configuration for high-performance setups.
+
+## 1\. Building the Docker Image
+
+The Dockerfile includes specific **Build Arguments** to allow you to selectively rebuild layers (e.g., update the vLLM source code without re-downloading PyTorch).
+
+### Option A: Standard Build (First Time)
+
+```bash
+docker build -t vllm-node .
+```
+
+### Option B: Fast Rebuild (Update vLLM Source Only)
+
+Use this if you want to pull the latest code from GitHub but keep the heavy dependencies (Torch, FlashInfer, system deps) cached.
+
+```bash
+docker build \
+  --build-arg CACHEBUST_VLLM=$(date +%s) \
+  -t vllm-node .
+```
+
+### Option C: Full Rebuild (Update All Dependencies)
+
+Use this to force a re-download of PyTorch, FlashInfer, and system packages.
+
+```bash
+docker build \
+  --build-arg CACHEBUST_DEPS=$(date +%s) \
+  -t vllm-node .
+```
+
+-----
+
+## 2\. Running the Container
+
+Ray and NCCL require specific Docker flags to function correctly across multiple nodes (Shared memory, Network namespace, and Hardware access).
+
+```bash
+docker run -it --rm \
+  --gpus all \
+  --net=host \
+  --ipc=host \
+  --privileged \
+  --name vllm_node \
+  vllm-node bash
+```
+
+**Flags Explained:**
+
+  * `--net=host`: **Required.** Ray needs full control over network ports; port mapping is insufficient for multi-node clusters.
+  * `--ipc=host`: **Required.** Allows shared memory access for PyTorch/NCCL.
+  * `--privileged`: **Required for InfiniBand.** Grants the container access to RDMA devices (`/dev/infiniband`).
+
+-----
+
+## 3\. Using `run-cluster-node.sh`
+
+Once inside the container, use the included script to configure the environment and launch Ray.
+
+### Syntax
+
+```bash
+./run-cluster-node.sh [OPTIONS]
+```
+
+| Flag | Long Flag | Description | Required? |
+| :--- | :--- | :--- | :--- |
+| `-r` | `--role` | Role of the machine: `head` or `node`. | **Yes** |
+| `-h` | `--host-ip` | The IP address of **this** specific machine (IB or Eth IP). | **Yes** |
+| `-e` | `--eth-if` | Ethernet interface name (e.g., `eth0`, `enp3s0`). | **Yes** |
+| `-i` | `--ib-if` | InfiniBand interface name (e.g., `ib0`, `rocep1s0f1`). | **Yes** |
+| `-m` | `--head-ip` | The IP address of the **Head Node**. | Only if role is `node` |
+
+### Example: Starting the Head Node
+
+```bash
+./run-cluster-node.sh \
+  --role head \
+  --host-ip 192.168.177.11 \
+  --eth-if enp1s0f1np1 \
+  --ib-if rocep1s0f1
+```
+
+### Example: Starting a Worker Node
+
+```bash
+./run-cluster-node.sh \
+  --role node \
+  --host-ip 192.168.177.12 \
+  --eth-if enp1s0f1np1 \
+  --ib-if rocep1s0f1 \
+  --head-ip 192.168.177.11
+```
+
+-----
+
+## 4\. Configuration Details
+
+### Environment Persistence
+
+The script automatically appends exported variables to `~/.bashrc`. If you need to open a second terminal into the running container for debugging, simply run:
+
+```bash
+docker exec -it vllm_node bash
+```
+
+All environment variables (NCCL, Ray, vLLM config) set by the startup script will be loaded automatically in this new session.
+
+### Hardware Architecture
+
+**Note:** The Dockerfile defaults to `TORCH_CUDA_ARCH_LIST=12.1a` (NVIDIA GB10). If you are using different hardware, update the `ENV` variable in the Dockerfile before building:
+
+  * **H100:** `9.0`
+  * **A100:** `8.0`
+  * **L40S:** `8.9`
diff --git a/run-cluster-node.sh b/run-cluster-node.sh
new file mode 100755
index 0000000..345659d
--- /dev/null
+++ b/run-cluster-node.sh
@@ -0,0 +1,118 @@
+#!/bin/bash
+set -e
+
+# Define a function to export immediately AND save to .bashrc for future sessions
+export_persist() {
+    local var_name="$1"
+    local var_value="$2"
+    
+    # 1. Export for the current running process
+    export "$var_name"="$var_value"
+    
+    # 2. Append to .bashrc (idempotent check to avoid duplicate lines)
+    if ! grep -q "export $var_name=" ~/.bashrc; then
+        echo "export $var_name=\"$var_value\"" >> ~/.bashrc
+    else
+        # Optional: Update the existing line if it exists
+        sed -i "s|export $var_name=.*|export $var_name=\"$var_value\"|" ~/.bashrc
+    fi
+}
+
+# --- Help Function ---
+usage() {
+    echo "Usage: $0 [OPTIONS]"
+    echo ""
+    echo "Required Arguments:"
+    echo "  -r, --role <head|node>      : Set the node type"
+    echo "  -h, --host-ip <ip>          : IP address of this interface (Host IP)"
+    echo "  -e, --eth-if <name>         : Ethernet interface name (e.g., eth0)"
+    echo "  -i, --ib-if <name>          : InfiniBand/RDMA interface name"
+    echo ""
+    echo "Conditional Arguments:"
+    echo "  -m, --head-ip <ip>          : IP of the head node (REQUIRED if role is 'node')"
+    echo ""
+    echo "Example:"
+    echo "  $0 --role head --host-ip 192.168.1.10 --eth-if eth0 --ib-if ib0"
+    echo "  $0 --role node --host-ip 192.168.1.20 --eth-if eth0 --ib-if ib0 --head-ip 192.168.1.10"
+    exit 1
+}
+
+# --- Argument Parsing ---
+
+# Initialize variables to empty
+NODE_TYPE=""
+HOST_IP=""
+ETH_IF_NAME=""
+IB_IF_NAME=""
+HEAD_IP=""
+
+while [[ "$#" -gt 0 ]]; do
+    case $1 in
+        -r|--role) NODE_TYPE="$2"; shift ;;
+        -h|--host-ip) HOST_IP="$2"; shift ;;
+        -e|--eth-if) ETH_IF_NAME="$2"; shift ;;
+        -i|--ib-if) IB_IF_NAME="$2"; shift ;;
+        -m|--head-ip) HEAD_IP="$2"; shift ;;
+        *) echo "Unknown parameter passed: $1"; usage ;;
+    esac
+    shift
+done
+
+# --- Validation ---
+
+# 1. Check if all common required arguments are present
+if [[ -z "$NODE_TYPE" || -z "$HOST_IP" || -z "$ETH_IF_NAME" || -z "$IB_IF_NAME" ]]; then
+    echo "Error: Missing required arguments."
+    usage
+fi
+
+# 2. Validate Role
+if [[ "$NODE_TYPE" != "head" && "$NODE_TYPE" != "node" ]]; then
+    echo "Error: --role must be 'head' or 'node'."
+    exit 1
+fi
+
+# 3. Conditional Check for Head IP
+if [[ "$NODE_TYPE" == "node" && -z "$HEAD_IP" ]]; then
+    echo "Error: When --role is 'node', you must provide --head-ip."
+    exit 1
+fi
+
+# --- Environment Configuration ---
+
+echo "Configuring environment for [$NODE_TYPE] at $HOST_IP..."
+
+export_persist VLLM_HOST_IP=$HOST_IP
+export_persist RAY_NODE_IP_ADDRESS=$VLLM_HOST_IP
+export_persist RAY_OVERRIDE_NODE_IP_ADDRESS=$VLLM_HOST_IP
+
+# Network Interface
+export_persist MN_IF_NAME=$ETH_IF_NAME
+export_persist UCX_NET_DEVICES=$MN_IF_NAME
+export_persist NCCL_SOCKET_IFNAME=$MN_IF_NAME
+
+# InfiniBand
+export_persist NCCL_IB_HCA=$IB_IF_NAME
+export_persist NCCL_IB_DISABLE=0
+
+# Sockets/Transport
+export_persist OMPI_MCA_btl_tcp_if_include=$MN_IF_NAME
+export_persist GLOO_SOCKET_IFNAME=$MN_IF_NAME
+export_persist TP_SOCKET_IFNAME=$MN_IF_NAME
+export_persist RAY_memory_monitor_refresh_ms=0
+
+# --- Execution ---
+
+if [ "${NODE_TYPE}" == "head" ]; then
+    echo "Starting Ray HEAD node..."
+    exec ray start --block --head --port 6379 \
+        --node-ip-address "$VLLM_HOST_IP" \
+        --dashboard-host "0.0.0.0" \
+        --dashboard-port 8265
+else
+    echo "Starting Ray WORKER node connecting to $HEAD_IP..."
+    exec ray start --block \
+        --address="$HEAD_IP:6379" \
+        --node-ip-address "$VLLM_HOST_IP"
+fi
+