ipex-llm/python/llm/example/GPU/HF-Transformers-AutoModels/Model/qwen1.5/README.md

Qwen1.5

In this directory, you will find examples on how you could apply BigDL-LLM INT4 optimizations on Qwen1.5 models on Intel GPUs. For illustration purposes, we utilize the Qwen/Qwen1.5-7B-Chat as a reference InternLM model.

0. Requirements

To run these examples with BigDL-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 Qwen1.5 model to predict the next N tokens using generate() API, with BigDL-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=3.9
conda activate llm
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
pip install --pre --upgrade bigdl-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu
pip install transformers==4.37.0 # install transformers which supports Qwen2

1.2 Installation on Windows

We suggest using conda to manage environment:

conda create -n llm python=3.9 libuv
conda activate llm
# below command will install intel_extension_for_pytorch==2.1.10+xpu as default
pip install --pre --upgrade bigdl-llm[xpu] -f https://developer.intel.com/ipex-whl-stable-xpu
pip install transformers==4.37.2 # install transformers which supports Qwen2

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

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 huggingface repo id for the Qwen1.5 model (e.g. Qwen/Qwen1.5-7B-Chat) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'Qwen/Qwen1.5-7B-Chat'.
• --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

Qwen/Qwen1.5-7B-Chat

Inference time: xxxx s
-------------------- Prompt --------------------
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
AI是什么？<|im_end|>
<|im_start|>assistant
-------------------- Output --------------------
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
AI是什么？<|im_end|>
<|im_start|>assistant
人工智能（AI）是指通过计算机模拟、延伸和扩展人类智能的学科，其目标是使机器具有学习、推理、感知、理解、交流

Inference time: xxxx s
-------------------- Prompt --------------------
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
What is AI?<|im_end|>
<|im_start|>assistant
-------------------- Output --------------------
<|im_start|>system
You are a helpful assistant.<|im_end|>
<|im_start|>user
What is AI?<|im_end|>
<|im_start|>assistant
AI, or artificial intelligence, refers to the simulation of human intelligence in machines that are programmed to perform tasks that typically require human cognition, such as learning, reasoning