ipex-llm/python/llm/example/GPU/ModelScope-Models

Run ModelScope Model

In this directory, you will find example on how you could apply IPEX-LLM INT4 optimizations on ModelScope models on Intel GPUs. For illustration purposes, we utilize the ZhipuAI/chatglm3-6b as a reference ModelScope model.

0. Requirements

To run these examples with IPEX-LLM on Intel GPUs, we have some recommended requirements for your machine, please refer to here for more information.

Example: Predict Tokens using generate() API

In the example generate.py, we show a basic use case for a ChatGLM3 model to predict the next N tokens using generate() API, with IPEX-LLM INT4 optimizations on Intel GPUs.

1. Install

1.1 Installation on Linux

We suggest using conda to manage environment:

conda create -n llm python=3.11
conda activate llm
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
# Refer to https://github.com/modelscope/modelscope/issues/765, please make sure you are using 1.11.0 version
pip install modelscope==1.11.0

1.2 Installation on Windows

We suggest using conda to manage environment:

conda create -n llm python=3.11 libuv
conda activate llm
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
pip install --pre --upgrade ipex-llm[xpu] --extra-index-url https://pytorch-extension.intel.com/release-whl/stable/xpu/us/
pip install modelscope

2. Configures OneAPI environment variables

2.1 Configurations for Linux

source /opt/intel/oneapi/setvars.sh

2.2 Configurations for Windows

call "C:\Program Files (x86)\Intel\oneAPI\setvars.bat"

Note: Please make sure you are using CMD (Anaconda Prompt if using conda) to run the command as PowerShell is not supported.

3. Runtime Configurations

For optimal performance, it is recommended to set several environment variables. Please check out the suggestions based on your device.

3.1 Configurations for Linux

For Intel Arc™ A-Series Graphics and Intel Data Center GPU Flex Series

```bash export USE_XETLA=OFF export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1 ```

For Intel Data Center GPU Max Series

export LD_PRELOAD=${LD_PRELOAD}:${CONDA_PREFIX}/lib/libtcmalloc.so
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=1
export ENABLE_SDP_FUSION=1

Note: Please note that libtcmalloc.so can be installed by conda install -c conda-forge -y gperftools=2.10.

3.2 Configurations for Windows

For Intel iGPU

set SYCL_CACHE_PERSISTENT=1
set BIGDL_LLM_XMX_DISABLED=1

For Intel Arc™ A300-Series or Pro A60

set SYCL_CACHE_PERSISTENT=1

For other Intel dGPU Series

There is no need to set further environment variables.

Note: For the first time that each model runs on Intel iGPU/Intel Arc™ A300-Series or Pro A60, it may take several minutes to compile.

4. Running examples

python ./generate.py --repo-id-or-model-path REPO_ID_OR_MODEL_PATH --prompt PROMPT --n-predict N_PREDICT

Arguments info:

• --repo-id-or-model-path REPO_ID_OR_MODEL_PATH: argument defining the ModelScope repo id for the ModelScope ChatGLM3 model to be downloaded, or the path to the ModelScope checkpoint folder. It is default to be 'ZhipuAI/chatglm3-6b'.
• --prompt PROMPT: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be 'AI是什么？'.
• --n-predict N_PREDICT: argument defining the max number of tokens to predict. It is default to be 32.

Sample Output

ZhipuAI/chatglm3-6b

Inference time: xxxx s
-------------------- Prompt --------------------
<|user|>
AI是什么？
<|assistant|>
-------------------- Output --------------------
[gMASK]sop <|user|>
AI是什么？
<|assistant|> AI是人工智能（Artificial Intelligence）的缩写，指的是通过计算机程序和算法模拟人类智能的技术。AI可以帮助我们解决各种问题，例如语音

Inference time: xxxx s
-------------------- Prompt --------------------
<|user|>
What is AI?
<|assistant|>
-------------------- Output --------------------
[gMASK]sop <|user|>
What is AI?
<|assistant|>
AI stands for Artificial Intelligence. It refers to the development of computer systems that can perform tasks that would normally require human intelligence, such as recognizing speech or making