OpenVINO™ GenAI is a library of most popular Generative AI model pipelines, optimized execution methods and samples that runs on top of highly performant OpenVINO Runtime.
Library is friendly to PC and laptop execution, optimized for resource consumption and requires no external dependencies to run generative models and includes all required functionality (e.g. tokenization via openvino-tokenizers).
OpenVINO™ GenAI library provides very lightweight C++ and Python APIs to run following Generative Scenarios:
- Text generation using Large Language Models. For example, chat with local LLaMa model
- Image generation using Diffuser models, for example generation using Stable Diffusion models
- Speech recognition using Whisper family models
- Text generation using Large Visual Models, for instance Image analysis using LLaVa or miniCPM models family
Library efficiently supports LoRA adapters for Text and Image generation scenarios:
- Load multiple adapters per model
- Select active adapters for every generation
- Mix multiple adapters with coefficients via alpha blending
All scenarios are run on top of OpenVINO Runtime that supports inference on CPU, GPU and NPU. See here for platform support matrix.
OpenVINO™ GenAI library provides transparent way to use state of the art generation optimizations:
- Speculative decoding that employs two models of different size and uses large model to periodically correct results of small model. See here for more detailed overview
- KVCache token eviction algorithm that reduces size of the KVCache by pruning less impacting tokens.
Additionally, OpenVINO™ GenAI library implements continuous batching approach to use OpenVINO within LLM serving. Continuous batching library could be used in LLM serving frameworks and supports following features:
- Prefix caching that caches fragments of previous generation requests and corresponding KVCache entries internally and uses them in case of repeated query. See here for more detailed overview
Continuous batching functionality is used within OpenVINO Model Server (OVMS) to serve LLMs, see here for more details.
# Installing OpenVINO GenAI via pip
pip install openvino-genai
# Install optimum-intel to be able to download, convert and optimize LLMs from Hugging Face
# Optimum is not required to run models, only to convert and compress
pip install optimum-intel@git+https://github.com/huggingface/optimum-intel.git
# (Optional) Install (TBD) to be able to download models from Model Scope#(Basic) download and convert to OpenVINO TinyLlama-Chat-v1.0 model
optimum-cli export openvino --model "TinyLlama/TinyLlama-1.1B-Chat-v1.0" --weight-format fp16 --trust-remote-code "TinyLlama-1.1B-Chat-v1.0"
#(Recommended) download, convert to OpenVINO and compress to int4 TinyLlama-Chat-v1.0 model
optimum-cli export openvino --model "TinyLlama/TinyLlama-1.1B-Chat-v1.0" --weight-format int4 --trust-remote-code "TinyLlama-1.1B-Chat-v1.0"import openvino_genai as ov_genai
#Will run model on CPU, GPU or NPU are possible options
pipe = ov_genai.LLMPipeline("./TinyLlama-1.1B-Chat-v1.0/", "CPU")
print(pipe.generate("The Sun is yellow because", max_new_tokens=100))Code below requires installation of C++ compatible package (see here for more details)
#include "openvino/genai/llm_pipeline.hpp"
#include <iostream>
int main(int argc, char* argv[]) {
std::string model_path = argv[1];
ov::genai::LLMPipeline pipe(model_path, "CPU");
std::cout << pipe.generate("The Sun is yellow because", ov::genai::max_new_tokens(100));
}(TBD)
#Download and convert to OpenVINO dreamlike-anime-1.0 model
optimum-cli export openvino --model dreamlike-art/dreamlike-anime-1.0 --task stable-diffusion --weight-format fp16 dreamlike_anime_1_0_ov/FP16#WIPCode below requires installation of C++ compatible package (see here for more details)
#include "openvino/genai/text2image/pipeline.hpp"
#include "imwrite.hpp"
int main(int argc, char* argv[]) {
const std::string models_path = argv[1], prompt = argv[2];
const std::string device = "CPU"; // GPU, NPU can be used as well
ov::genai::Text2ImagePipeline pipe(models_path, device);
ov::Tensor image = pipe.generate(prompt,
ov::genai::width(512),
ov::genai::height(512),
ov::genai::num_inference_steps(20));
imwrite("image.bmp", image, true);
}(TBD)
NOTE: Whisper Pipeline requires preprocessing of audio input (to adjust sampling rate and normalize)
#Download and convert to OpenVINO whisper-base model
optimum-cli export openvino --trust-remote-code --model openai/whisper-base whisper-baseNOTE: this sample is simplified version of full sample that is available here
import argparse
import openvino_genai
import librosa
def read_wav(filepath):
raw_speech, samplerate = librosa.load(filepath, sr=16000)
return raw_speech.tolist()
def main():
parser = argparse.ArgumentParser()
parser.add_argument("model_dir")
parser.add_argument("wav_file_path")
args = parser.parse_args()
raw_speech = read_wav(args.wav_file_path)
pipe = openvino_genai.WhisperPipeline(args.model_dir)
def streamer(word: str) -> bool:
print(word, end="")
return False
pipe.generate(
raw_speech,
max_new_tokens=100,
# 'task' and 'language' parameters are supported for multilingual models only
language="<|en|>",
task="transcribe",
streamer=streamer,
)
print()NOTE: this sample is simplified version of full sample that is available here
#include "audio_utils.hpp"
#include "openvino/genai/whisper_pipeline.hpp"
int main(int argc, char* argv[]) try {
std::string model_path = argv[1];
std::string wav_file_path = argv[2];
ov::genai::RawSpeechInput raw_speech = utils::audio::read_wav(wav_file_path);
ov::genai::WhisperPipeline pipeline{model_path};
ov::genai::WhisperGenerationConfig config{model_path + "/generation_config.json"};
config.max_new_tokens = 100;
// 'task' and 'language' parameters are supported for multilingual models only
config.language = "<|en|>";
config.task = "transcribe";
auto streamer = [](std::string word) {
std::cout << word;
return false;
};
pipeline.generate(raw_speech, config, streamer);
std::cout << std::endl;
}(TBD)
- List of supported models (NOTE: models can work, but were not tried yet)
- OpenVINO LLM inference Guide
- Optimum-intel and OpenVINO
The OpenVINO™ GenAI repository is licensed under Apache License Version 2.0. By contributing to the project, you agree to the license and copyright terms therein and release your contribution under these terms.