Skip to content

Latest commit

 

History

History
155 lines (111 loc) · 5.46 KB

README.md

File metadata and controls

155 lines (111 loc) · 5.46 KB
Raw

Llama3.2

In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on Llama3.2 models on Intel GPUs. For illustration purposes, we utilize the meta-llama/Meta-Llama-3.2-3B-Instruct and meta-llama/Meta-Llama-3.2-1B-Instruct as reference Llama3.2 models.

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 Llama3.2 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/

pip install transformers==4.45.0
pip install accelerate==0.33.0
pip install trl

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 transformers==4.45.0
pip install accelerate==0.33.0
pip install trl

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
export BIGDL_LLM_XMX_DISABLED=1

3.2 Configurations for Windows

For Intel iGPU 
set SYCL_CACHE_PERSISTENT=1
set BIGDL_LLM_XMX_DISABLED=1
For 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 Llama3.2 model (e.g. meta-llama/Meta-Llama-3.2-3B-Instruct) to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'meta-llama/Meta-Llama-3.2-3B-Instruct'.
  • --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

meta-llama/Meta-Llama-3.2-3B-Instruct

Inference time: xxxx s
-------------------- Prompt --------------------
<|begin_of_text|><|start_header_id|>user<|end_header_id|>

What is AI?<|eot_id|><|start_header_id|>assistant<|end_header_id|>


-------------------- Output (skip_special_tokens=False) --------------------
<|begin_of_text|><|begin_of_text|><|start_header_id|>user<|end_header_id|>

What is AI?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Artificial Intelligence (AI) refers to the development of computer systems that can perform tasks that would typically require human intelligence, such as learning, problem-solving, and

meta-llama/Meta-Llama-3.2-1B-Instruct

Inference time: xxxx s
-------------------- Prompt --------------------
<|begin_of_text|><|start_header_id|>user<|end_header_id|>

What is AI?<|eot_id|><|start_header_id|>assistant<|end_header_id|>


-------------------- Output (skip_special_tokens=False) --------------------
<|begin_of_text|><|begin_of_text|><|start_header_id|>user<|end_header_id|>

What is AI?<|eot_id|><|start_header_id|>assistant<|end_header_id|>

Artificial Intelligence (AI) refers to the development of computer systems that can perform tasks that typically require human intelligence, such as learning, problem-solving, and decision