internlm

InternLM

In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on InternLM models on Intel GPUs. For illustration purposes, we utilize the internlm/internlm-chat-7b as a reference InternLM 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 InternLM 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/

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/

2. Configures OneAPI environment variables for Linux

Note

Skip this step if you are running on Windows.

This is a required step on Linux for APT or offline installed oneAPI. Skip this step for PIP-installed oneAPI.

source /opt/intel/oneapi/setvars.sh

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
export SYCL_CACHE_PERSISTENT=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 SYCL_CACHE_PERSISTENT=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.

For Intel iGPU

export SYCL_CACHE_PERSISTENT=1

3.2 Configurations for Windows

For Intel iGPU and Intel Arc™ A-Series Graphics

set SYCL_CACHE_PERSISTENT=1

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 InternLM model (e.g. internlm/internlm-chat-7b) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'internlm/internlm-chat-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 be 32.

Sample Output

internlm/internlm-chat-7b

Inference time: xxxx s
-------------------- Prompt --------------------
<|User|>:AI是什么？
<|Bot|>:
-------------------- Output --------------------
<|User|>:AI是什么？
<|Bot|>:AI是人工智能的缩写，是计算机科学的一个分支，旨在使计算机能够像人类一样思考、学习和执行任务。AI技术包括机器学习、自然

Inference time: xxxx s
-------------------- Prompt --------------------
<|User|>:What is AI?
<|Bot|>:
-------------------- Output --------------------
<|User|>:What is AI?
<|Bot|>:AI is the ability of machines to perform tasks that would normally require human intelligence, such as perception, reasoning, learning, and decision-making. AI is made possible