Skip to main content


IPEX-LLM is a PyTorch library for running LLM on Intel CPU and GPU (e.g., local PC with iGPU, discrete GPU such as Arc, Flex and Max) with very low latency.

This example goes over how to use LangChain to interact with ipex-llm for text generation.


# Update Langchain

%pip install -qU langchain langchain-community

Install IEPX-LLM for running LLMs locally on Intel CPU.

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

Basic Usage

import warnings

from langchain.chains import LLMChain
from langchain_community.llms import IpexLLM
from langchain_core.prompts import PromptTemplate

warnings.filterwarnings("ignore", category=UserWarning, message=".*padding_mask.*")
API Reference:LLMChain | IpexLLM | PromptTemplate

Specify the prompt template for your model. In this example, we use the vicuna-1.5 model. If you're working with a different model, choose a proper template accordingly.

template = "USER: {question}\nASSISTANT:"
prompt = PromptTemplate(template=template, input_variables=["question"])

Load the model locally using IpexLLM using IpexLLM.from_model_id. It will load the model directly in its Huggingface format and convert it automatically to low-bit format for inference.

llm = IpexLLM.from_model_id(
model_kwargs={"temperature": 0, "max_length": 64, "trust_remote_code": True},

Use it in Chains:

llm_chain = prompt | llm

question = "What is AI?"
output = llm_chain.invoke(question)

Save/Load Low-bit Model

Alternatively, you might save the low-bit model to disk once and use from_model_id_low_bit instead of from_model_id to reload it for later use - even across different machines. It is space-efficient, as the low-bit model demands significantly less disk space than the original model. And from_model_id_low_bit is also more efficient than from_model_id in terms of speed and memory usage, as it skips the model conversion step.

To save the low-bit model, use save_low_bit as follows.

saved_lowbit_model_path = "./vicuna-7b-1.5-low-bit"  # path to save low-bit model
del llm

Load the model from saved lowbit model path as follows.

Note that the saved path for the low-bit model only includes the model itself but not the tokenizers. If you wish to have everything in one place, you will need to manually download or copy the tokenizer files from the original model's directory to the location where the low-bit model is saved.

llm_lowbit = IpexLLM.from_model_id_low_bit(
# tokenizer_name=saved_lowbit_model_path, # copy the tokenizers to saved path if you want to use it this way
model_kwargs={"temperature": 0, "max_length": 64, "trust_remote_code": True},

Use the loaded model in Chains:

llm_chain = prompt | llm_lowbit

question = "What is AI?"
output = llm_chain.invoke(question)

Was this page helpful?

You can leave detailed feedback on GitHub.