Skip to content

Latest commit

 

History

History
149 lines (113 loc) · 5.82 KB

README.md

File metadata and controls

149 lines (113 loc) · 5.82 KB
Raw

Gemma

In this directory, you will find examples on how you could apply BigDL-LLM INT4 optimizations on Google Gemma models on Intel GPUs. For illustration purposes, we utilize the google/gemma-7b-it and google/gemma-2b-it as reference Gemma models.

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.

Important: According to Gemma's requirement, please make sure you have installed transformers==4.38.1 to run the example.

Example: Predict Tokens using generate() API

In the example generate.py, we show a basic use case for a Gemma 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 the Python environment. For more information about conda installation, please refer to here.

After installing conda, create a Python environment for BigDL-LLM:

conda create -n llm python=3.9 # recommend to use 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

# According to Gemma's requirement, please make sure you are using a stable version of Transformers, 4.38.1 or newer.
pip install transformers==4.38.1

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

# According to Gemma's requirement, please make sure you are using a stable version of Transformers, 4.38.1 or newer.
pip install transformers==4.38.1

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 --prompt 'What is AI?'

In the example, several arguments can be passed to satisfy your requirements:

  • --repo-id-or-model-path REPO_ID_OR_MODEL_PATH: argument defining the huggingface repo id for the Gemma model (e.g. google/gemma-7b-it and google/gemma-2b-it) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'google/gemma-7b-it'.
  • --prompt PROMPT: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be 'What is AI?'.
  • --n-predict N_PREDICT: argument defining the max number of tokens to predict. It is default to be 32.
Sample Output
google/gemma-7b-it
Inference time: xxxx s
-------------------- Output --------------------
user
What is AI?
model
**Artificial Intelligence (AI)** is a field of computer science that involves the creation of intelligent machines capable of performing tasks typically requiring human intelligence, such as learning,
google/gemma-2b-it
Inference time: xxxx s
-------------------- Output --------------------
user
What is AI?
model
**Artificial intelligence (AI)** is the simulation of human cognitive functions, such as learning, reasoning, and problem-solving, by machines. AI systems are designed

5. Know issue

1. Random and unreadable output of Gemma-7b-it on Arc770 ubuntu 22.04 due to driver and OneAPI missmatching.

If driver and OneAPI missmatching, it will lead to some error when BigDL use XMX(short prompts) for speeding up. The output of What's AI? may like below:

wiedzy Artificial Intelligence meliti: Artificial Intelligence undenti beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng beng

If you meet this error. Please check your driver version and OneAPI version. Commnad is sudo apt list --installed | egrep "intel-basekit|intel-level-zero-gpu". Make sure intel-basekit>=2024.0.1-43 and intel-level-zero-gpu>=1.3.27191.42-775~22.04.