Further supplement installation guide

Signed-off-by: Gaohan123 <gaohan19@huawei.com>

README.md

@@ -38,18 +38,31 @@ vLLM-omni is built on a modular architecture that extends vLLM's core functional
 
 ## 🛠️ Installation
 
-Set up basic environments
+Use Docker to keep consistent basic environment (Optional, Recommended)
+```bash
+docker run --gpus all --ipc=host --network=host -v $source_dir:$container_dir --rm --name $container_name -it nvcr.io/nvidia/pytorch:25.01-py3 bash
+```
+
+Set up basic uv environment
 ```bash
 uv venv --python 3.12 --seed
 source .venv/bin/activate
 ```
 Install certain version of vllm with commitid: 808a7b69df479b6b3a16181711cac7ca28a9b941
 
+```bash
+git clone https://github.com/vllm-project/vllm.git
+cd vllm
+git checkout 808a7b69df479b6b3a16181711cac7ca28a9b941
+```
+Set up environment variables to get pre-built wheels. If there are internet problems, just download the whl file manually. And set VLLM_PRECOMPILED_WHEEL_LOCATION as your local absolute path of whl file.
 ```bash
 export VLLM_COMMIT=808a7b69df479b6b3a16181711cac7ca28a9b941
-uv pip install vllm \
-    --torch-backend=auto \
-    --extra-index-url https://wheels.vllm.ai/${VLLM_COMMIT}
+export VLLM_PRECOMPILED_WHEEL_LOCATION=https://wheels.vllm.ai/${VLLM_COMMIT}/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl
+```
+Install vllm with commend below.
+```bash
+uv pip install --editable .
 ```
 Install additional requirements for vllm-omni
 ```bash

examples/offline_inference/qwen_2_5_omni/README.md

@@ -1,19 +1,32 @@
 # Offline Example of vLLM-omni for Qwen2.5-omni
 
-## Installation
+## 🛠️ Installation
 
-Set up basic environments
+Use Docker to keep consistent basic environment (Optional, Recommended)
+```bash
+docker run --gpus all --ipc=host --network=host -v $source_dir:$container_dir --rm --name $container_name -it nvcr.io/nvidia/pytorch:25.01-py3 bash
+```
+
+Set up basic uv environment
 ```bash
 uv venv --python 3.12 --seed
 source .venv/bin/activate
 ```
 Install certain version of vllm with commitid: 808a7b69df479b6b3a16181711cac7ca28a9b941
 
+```bash
+git clone https://github.com/vllm-project/vllm.git
+cd vllm
+git checkout 808a7b69df479b6b3a16181711cac7ca28a9b941
+```
+Set up environment variables to get pre-built wheels. If there are internet problems, just download the whl file manually. And set VLLM_PRECOMPILED_WHEEL_LOCATION as your local absolute path of whl file.
 ```bash
 export VLLM_COMMIT=808a7b69df479b6b3a16181711cac7ca28a9b941
-uv pip install vllm \
-    --torch-backend=auto \
-    --extra-index-url https://wheels.vllm.ai/${VLLM_COMMIT}
+export VLLM_PRECOMPILED_WHEEL_LOCATION=https://wheels.vllm.ai/${VLLM_COMMIT}/vllm-1.0.0.dev-cp38-abi3-manylinux1_x86_64.whl
+```
+Install vllm with commend below.
+```bash
+uv pip install --editable .
 ```
 
 ## Run examples

requirements.txt

@@ -1,10 +1,8 @@
 cloudpickle==3.1.1
-flash_attn==2.8.3
 msgspec==0.19.0
 numpy==2.3.4
 omegaconf==2.3.0
 pydantic==2.12.3
-torch==2.8.0
 transformers==4.57.0
 typing_extensions==4.15.0
 decord==0.6.0
@@ -14,4 +12,3 @@ Pillow==12.0.0
 Requests==2.32.5
 resampy==0.4.3
 soundfile==0.13.1
-torchvision==0.23.0