codegemma

CodeGemma

In this directory, you will find examples on how you could apply IPEX-LLM INT4 optimizations on CodeGemma models. For illustration purposes, we utilize the google/codegemma-7b-it as reference CodeGemma models.

0. Requirements

To run these examples with IPEX-LLM, 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 CodeGemma model to predict the next N tokens using generate() API, with IPEX-LLM INT4 optimizations.

1. Install

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 IPEX-LLM:

On Linux:

conda create -n llm python=3.11 # recommend to use Python 3.11
conda activate llm

# install ipex-llm with 'all' option
pip install --pre --upgrade ipex-llm[all] --extra-index-url https://download.pytorch.org/whl/cpu

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

On Windows:

conda create -n llm python=3.11
conda activate llm

pip install --pre --upgrade ipex-llm[all]

pip install "transformers>=4.38.1"

2. Run

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 CodeGemma model to be downloaded, or the path to the huggingface checkpoint folder. It is default to be 'google/codegemma-7b-it'.
• --prompt PROMPT: argument defining the prompt to be infered (with integrated prompt format for chat). It is default to be 'Write a hello world program'.
• --n-predict N_PREDICT: argument defining the max number of tokens to predict. It is default to be 32.

Note: When loading the model in 4-bit, IPEX-LLM converts linear layers in the model into INT4 format. In theory, a XB model saved in 16-bit will requires approximately 2X GB of memory for loading, and ~0.5X GB memory for further inference.

Please select the appropriate size of the CodeLlama model based on the capabilities of your machine.

2.1 Client

On client Windows machine, it is recommended to run directly with full utilization of all cores:

python ./generate.py 

2.2 Server

For optimal performance on server, it is recommended to set several environment variables (refer to here for more information), and run the example with all the physical cores of a single socket.

E.g. on Linux,

# set IPEX-LLM env variables
source ipex-llm-init

# e.g. for a server with 48 cores per socket
export OMP_NUM_THREADS=48
numactl -C 0-47 -m 0 python ./generate.py

2.3 Sample Output

google/codegemma-7b-it

Inference time: xxxx s
-------------------- Prompt --------------------
<bos><start_of_turn>user
Write a hello world program<end_of_turn>
<start_of_turn>model

-------------------- Output --------------------
<start_of_turn>user
Write a hello world program<end_of_turn>
<start_of_turn>model
```python
print("Hello, world!")

This program will print the message "Hello, world!" to the console.