Repository files navigation

🤗 Optimum Intel is the interface between the 🤗 Transformers and Diffusers libraries and the different tools and libraries provided by Intel to accelerate end-to-end pipelines on Intel architectures.

Intel Extension for PyTorch is an open-source library which provides optimizations like faster attention and operators fusion.

IntelNeural Compressor is an open-source library enabling the usage of the most popular compression techniques such as quantization, pruning and knowledge distillation. It supports automatic accuracy-driven tuning strategies in order for users to easily generate quantized model. The users can easily apply static, dynamic and aware-training quantization approaches while giving an expected accuracy criteria. It also supports different weight pruning techniques enabling the creation of pruned model giving a predefined sparsity target.

OpenVINO is an open-source toolkit that enables high performance inference capabilities for Intel CPUs, GPUs, and special DL inference accelerators (see the full list of supported devices). It is supplied with a set of tools to optimize your models with compression techniques such as quantization, pruning and knowledge distillation. Optimum Intel provides a simple interface to optimize your Transformers and Diffusers models, convert them to the OpenVINO Intermediate Representation (IR) format and run inference using OpenVINO Runtime.

To install the latest release of 🤗 Optimum Intel with the corresponding required dependencies, you can usepip as follows:

The--upgrade-strategy eager option is needed to ensureoptimum-intel is upgraded to the latest version.

We recommend creating avirtual environment and upgradingpip withpython -m pip install --upgrade pip.

Optimum Intel is a fast-moving project, and you may want to install from source with the following command:

python -m pip install git+https://github.com/huggingface/optimum-intel.git

or to install from source including dependencies:

python -m pip install"optimum-intel[extras]"@git+https://github.com/huggingface/optimum-intel.git

whereextras can be one or more ofipex,neural-compressor,openvino,nncf.

Dynamic quantization can be used through the Optimum command-line interface:

optimum-cli inc quantize --model distilbert-base-cased-distilled-squad --output ./quantized_distilbert

Note that quantization is currently only supported for CPUs (only CPU backends are available), so we will not be utilizing GPUs / CUDA in this example.

To load a quantized model hosted locally or on the 🤗 hub, you can do as follows :

fromoptimum.intelimportINCModelForSequenceClassificationmodel_id="Intel/distilbert-base-uncased-finetuned-sst-2-english-int8-dynamic"model=INCModelForSequenceClassification.from_pretrained(model_id)

You can load many more quantized models hosted on the hub under the Intel organizationhere.

For more details on the supported compression techniques, please refer to thedocumentation.

Below are examples of how to use OpenVINO and itsNNCF framework to accelerate inference.

It is also possible to export your model to theOpenVINO IR format with the CLI :

optimum-cli export openvino --model gpt2 ov_model

You can also apply 8-bit weight-only quantization when exporting your model : the model linear, embedding and convolution weights will be quantized to INT8, the activations will be kept in floating point precision.

optimum-cli export openvino --model gpt2 --weight-format int8 ov_model

Quantization in hybrid mode can be applied to Stable Diffusion pipeline during model export. This involves applying hybrid post-training quantization to the UNet model and weight-only quantization for the rest of the pipeline components. In the hybrid mode, weights in MatMul and Embedding layers are quantized, as well as activations of other layers.

optimum-cli export openvino --model stabilityai/stable-diffusion-2-1 --dataset conceptual_captions --weight-format int8 ov_model

To apply quantization on both weights and activations, you can find more information in thedocumentation.

To load a model and run inference with OpenVINO Runtime, you can just replace yourAutoModelForXxx class with the correspondingOVModelForXxx class.

- from transformers import AutoModelForSeq2SeqLM+ from optimum.intel import OVModelForSeq2SeqLM  from transformers import AutoTokenizer, pipeline  model_id = "echarlaix/t5-small-openvino"- model = AutoModelForSeq2SeqLM.from_pretrained(model_id)+ model = OVModelForSeq2SeqLM.from_pretrained(model_id)  tokenizer = AutoTokenizer.from_pretrained(model_id)  pipe = pipeline("translation_en_to_fr", model=model, tokenizer=tokenizer)  results = pipe("He never went out without a book under his arm, and he often came back with two.")  [{'translation_text': "Il n'est jamais sorti sans un livre sous son bras, et il est souvent revenu avec deux."}]

If you want to load a PyTorch checkpoint, setexport=True to convert your model to the OpenVINO IR.

fromoptimum.intelimportOVModelForCausalLMmodel=OVModelForCausalLM.from_pretrained("gpt2",export=True)model.save_pretrained("./ov_model")

Post-training static quantization introduces an additional calibration step where data is fed through the network in order to compute the activations quantization parameters. Here is an example on how to apply static quantization on a fine-tuned DistilBERT.

fromfunctoolsimportpartialfromoptimum.intelimportOVQuantizer,OVModelForSequenceClassification,OVConfig,OVQuantizationConfigfromtransformersimportAutoTokenizer,AutoModelForSequenceClassificationmodel_id="distilbert-base-uncased-finetuned-sst-2-english"model=OVModelForSequenceClassification.from_pretrained(model_id,export=True)tokenizer=AutoTokenizer.from_pretrained(model_id)defpreprocess_fn(examples,tokenizer):returntokenizer(examples["sentence"],padding=True,truncation=True,max_length=128    )quantizer=OVQuantizer.from_pretrained(model)calibration_dataset=quantizer.get_calibration_dataset("glue",dataset_config_name="sst2",preprocess_function=partial(preprocess_fn,tokenizer=tokenizer),num_samples=100,dataset_split="train",preprocess_batch=True,)# The directory where the quantized model will be savedsave_dir="nncf_results"# Apply static quantization and save the resulting model in the OpenVINO IR formatov_config=OVConfig(quantization_config=OVQuantizationConfig())quantizer.quantize(ov_config=ov_config,calibration_dataset=calibration_dataset,save_directory=save_dir)# Load the quantized modeloptimized_model=OVModelForSequenceClassification.from_pretrained(save_dir)

To load your IPEX model, you can just replace yourAutoModelForXxx class with the correspondingIPEXModelForXxx class. It will load a PyTorch checkpoint, and apply IPEX operators optimization (replaced with customized IPEX operators).

  from transformers import AutoTokenizer, pipeline- from transformers import AutoModelForCausalLM+ from optimum.intel import IPEXModelForCausalLM  model_id = "gpt2"- model = AutoModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)+ model = IPEXModelForCausalLM.from_pretrained(model_id, torch_dtype=torch.bfloat16)  tokenizer = AutoTokenizer.from_pretrained(model_id)  pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)  results = pipe("He's a dreadful magician and")

For more details, please refer to thedocumentation.

Check out theexamples andnotebooks directory to see how 🤗 Optimum Intel can be used to optimize models and accelerate inference.

Do not forget to install requirements for every example:

cd <example-folder>pip install -r requirements.txt

To train your model onIntel Gaudi AI Accelerators (HPU), check outOptimum Habana which provides a set of tools enabling easy model loading, training and inference on single- and multi-HPU settings for different downstream tasks. After training your model, feel free to submit it to the Intelleaderboard which is designed to evaluate, score, and rank open-source LLMs that have been pre-trained or fine-tuned on Intel Hardwares. Models submitted to the leaderboard will be evaluated on the Intel Developer Cloud. The evaluation platform consists of Gaudi Accelerators and Xeon CPUs running benchmarks from the Eleuther AI Language Model Evaluation Harness.