Add Multi-Environment Support for Nano-vLLM

Dockerfile

@@ -0,0 +1,40 @@
+# Use NVIDIA CUDA runtime with cuDNN
+FROM nvidia/cuda:12.1.105-cudnn8-runtime-ubuntu22.04
+
+# Set environment variables to avoid Python buffering and warnings
+ENV PYTHONUNBUFFERED=1
+ENV DEBIAN_FRONTEND=noninteractive
+
+# Install Python 3.10 and pip
+RUN apt-get update && apt-get install -y \
+    python3.10 \
+    python3.10-distutils \
+    python3-pip \
+    && rm -rf /var/lib/apt/lists/*
+
+# Upgrade pip
+RUN python3.10 -m pip install --upgrade pip
+
+# Set working directory
+WORKDIR /app
+
+# Copy requirements and install
+COPY requirements.txt .
+RUN python3.10 -m pip install --no-cache-dir -r requirements.txt
+
+# Copy the rest of the application
+COPY . .
+
+<<<<<<< HEAD
+# Create volume for models or data
+VOLUME ["/app/models"]
+
+# Default command to run example.py
+CMD ["python3.10", "example.py"]
+=======
+# Create volume for data
+VOLUME ["/app/data"]
+
+# Default command to run example
+CMD ["python3", "example.py"]
+>>>>>>> 4906eee39bbe85c6561aca5f93b76d0d8e32bdce

README.md

@@ -10,6 +10,36 @@ A lightweight vLLM implementation built from scratch.
 
 ## Installation
 
+### Option 1: Pip Installation
+
+Clone the repository and install dependencies using pip:
+
+```bash
+git clone https://github.com/BaoZhuhan/nano-vllm.git
+cd nano-vllm
+pip install -r requirements.txt
+```
+
+### Option 2: Conda Environment
+
+Create a conda environment with all dependencies:
+
+```bash
+conda env create -f environment.yml
+conda activate nano-vllm
+```
+
+### Option 3: Docker
+
+Build and run using Docker (requires NVIDIA GPU support):
+
+```bash
+docker build -t nano-vllm .
+docker run --gpus all -v /path/to/models:/app/models nano-vllm
+```
+
+For manual installation from source:
+
 ```bash
 pip install git+https://github.com/GeeeekExplorer/nano-vllm.git
 ```

environment.yml

@@ -0,0 +1,17 @@
+name: nano-vllm
+channels:
+  - pytorch
+  - nvidia
+  - conda-forge
+dependencies:
+  - python=3.10
+  - pytorch>=2.4.0
+  - torchvision
+  - torchaudio
+  - pytorch-cuda=12.1
+  - pip
+  - pip:
+    - triton>=3.0.0
+    - transformers>=4.51.0
+    - flash-attn
+    - xxhash

requirements.txt

@@ -0,0 +1,5 @@
+torch>=2.4.0
+triton>=3.0.0
+transformers>=4.51.0
+flash-attn
+xxhash