In this directory, you will find examples on how you could apply BigDL-LLM INT4 optimizations on RWKV4 models on Intel GPUs. For illustration purposes, we utilize the RWKV/rwkv-4-world-7b as a reference RWKV4 model.
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.
In the example generate.py, we show a basic use case for a RWKV4 model to predict the next N tokens using generate() API, with BigDL-LLM INT4 optimizations on Intel GPUs.
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-xpuWe 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-xpusource /opt/intel/oneapi/setvars.shcall "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.
For optimal performance, it is recommended to set several environment variables. Please check out the suggestions based on your device.
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=1For 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=1Note: Please note that
libtcmalloc.socan be installed byconda install -c conda-forge -y gperftools=2.10.
For Intel iGPU
set SYCL_CACHE_PERSISTENT=1
set BIGDL_LLM_XMX_DISABLED=1For Intel Arc™ A300-Series or Pro A60
set SYCL_CACHE_PERSISTENT=1For 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.
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 RWKV4 model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be'RWKV/rwkv-4-world-7b'.--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 be32.
Inference time: xxxx s
-------------------- Prompt --------------------
User: hi
Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
User: AI是什么？
Assistant:
-------------------- Output --------------------
User: hi
Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
User: AI是什么？
Assistant: AI是人工智能的缩写，是指计算机系统的能力，使其能够模拟人类的智能
Inference time: xxxx s
-------------------- Prompt --------------------
User: hi
Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
User: What is AI?
Assistant:
-------------------- Output --------------------
User: hi
Assistant: Hi. I am your assistant and I will provide expert full response in full details. Please feel free to ask any question and I will always answer it.
User: What is AI?
Assistant: AI, or artificial intelligence, refers to the simulation of human intelligence processes by machines, especially computer systems. This includes the simulation of human perception, reasoning, learning