Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
Sort By:

Large Language Model Graph Customization with OpenVINO™ Transformations API

April 15, 2024

Authors: Xiake Sun, Wenyi Zou, Fiona Zhao


A Large Language Model (LLM) is a type of artificial intelligence algorithm that uses deep learning techniques and massively large data sets to understand, summarize, generate and predict new content.

OpenVINO™ optimizes the deployment of LLMs, enhancing their performance and integration into various applications. We already provide general guide to use LLMs with OpenVINO, from model loading and conversion to advanced use cases.

In this blog, we will introduce some useful method to customize Large Language model’s graph with OpenVINO™ transformation API.

OpenVINO™ Runtime has three main transformation types:

  • Modelpass: straightforward way to work with ov::Model directly
  • Matcherpass: pattern-based transformation approach
  • Graphrewrite pass: container for matcher passes needed for efficient execution.
Figure1. OpenVINO™ transformations API structure overview

In this blog, we mainly use ov::pass::MatcherPassto customize model subgraph via pattern-based transformation.

Here are common steps to implement graph customization using ov::pass::MatcherPass.

  1. Create a pattern
  2. Implement a callback
  3. Register the pattern and Matcher
  4. Execute MatcherPass

In this blog, we will use an open-source LLMs Qwen1.5-7B-Chat-GPTQ-Int4 from Alibaba Cloud with guide for model conversion and graph customization methods.

Qwen Pytorch to OpenVINO™ Model conversion

Here we can use openvino.genai repo to convert Qwen1.5 GPTQ INT4 Pytroch model to OpenVINO™model.

conda create -n openvino.genai python=3.10
git clone
cd llm_bench/python
pip install -r requirements.txt
python –model_id Qwen/Qwen1.5-7B-Chat-GPTQ-Int4 --output_dir  Qwen1.5-7B-Chat-GPTQ-Int4-OV --precision FP16 

Converted model can be find in path “Qwen1.5-7B-Chat-GPTQ-Int4-OV/pytorch/dldt/GPTQ_INT4-FP16/".

Insert custom layer to OpenVINO model

Vocabularysize in the context of LLMs refers to the total number of unique words, or tokens, that the model can recognize and use. The larger the vocabulary size,the more nuanced and detailed the model’s understanding of language can be,however, it also requires more computational and memory resources for deployment.  E.g. Qwen’s vocabulary size(151936) is almost 5x that Llama2 (32000), therefore additional optimization is required for efficient deployment.

We found that the following pattern existed in the Qwen model in Figure 2:

Figure 2: Workflow to reduce MatMul computation and memory usage for logits in Qwen model

To compute the first token generation for the input prompt with shape [1, seq_length], we need to calculate a MatMul operation based on two inputs.

  • First input is a reshape node output with shape[1, seq_length, 4096]
  • Second input is a constant value that contains the model’s vocabulary with shape [4096,151936]

Then Matmul calculates two inputs [1, seq_length, 4096] * [4096,151936] to output large logits [1, seq_length,151936]. However, for the next token prediction, we only need the last element [1,4096] in 1st dimension from logits for sampling.

The main idea is to insert a slice operation between Reshape and Matmul nodes to extract only the last element in 2nd dimension of reshape node output as the first input with shape [1,4096] for computation. Therefore, Matmul computation can be reduced from [1, seq_len, 4096] * [1, 4096, 151936] = [1, seq_len, 151936] to [1, 1, 4096] *[4096, 151936] = [1, 1, 151936], which can reduce first token latency and memory consumption.

Here is a sample code to implement the workflow defined in Figure2 to reduce Qwen's last Matmul computation and memory usage:

# -*- coding: utf-8 -*-
import numpy as np
import openvino as ov
from openvino.runtime import Core, Type
from openvino.runtime.passes import Manager, MatcherPass, WrapType, Matcher
from openvino.runtime import opset10 as ops
from openvino.preprocess import PrePostProcessor

class InsertSlice(MatcherPass):
    def __init__(self):
        self.model_changed = False

        param = WrapType("opset10.Result")

        def callback(matcher: Matcher) -> bool:
            root = matcher.get_match_root()
            print("root: ", root)
            if root is None:
                return False
            root_output = matcher.get_match_value()
            print("root_output", root_output)
            root_name = root.get_friendly_name()
            if (len(root.get_output_partial_shape(0)) == 3):
                print(f"Find target root node name: {root_name}")
                parent = root.input_value(0).get_node()
                print(f"Find target parent node name: {parent.get_friendly_name()}")
                grand_parent = parent.input_value(0).get_node()
                print(f"Find grandparent node name: {grand_parent.get_friendly_name()}")
                grand_parent_output = parent.input(0).get_source_output()
                print("grand_parent_output: ", grand_parent_output)
                consumers = grand_parent_output.get_target_inputs()
                print(f"consumers: {consumers}")
                print("Original reshape node output shape:", grand_parent_output.get_partial_shape())
                start = np.array([0, -1, 0], dtype=np.int32)
                stop = np.array([1, -2, 4096], dtype=np.int32)
                step = np.array([1, -1, 1], dtype=np.int32)
                axes = np.array([0, 1, 2], dtype=np.int32)
                slice = ops.slice(grand_parent, start, stop, step, axes, name="inserted_slice")
                print("After insert slice node, output shape:", slice.output(0).get_partial_shape())

                for consumer in consumers:
                self.model_changed = True
                # Use new operation for additional matching
                return True

        self.register_matcher(Matcher(param,"InsertSlice"), callback)

if __name__ == "__main__":
    model_path = " Qwen1.5-7B-Chat-GPTQ-Int4-OV/pytorch/dldt/GPTQ_INT4-FP16/ openvino_model.xml"
    modified_model_path = "Qwen1.5-7B-Chat-GPTQ-Int4-OV/pytorch/dldt/GPTQ_INT4-FP16/modified_openvino_model.xml")
    core = Core()
    ov_model = core.read_model(model_path)
    manager = Manager()
    ov.save_model(ov_model, modified_model_path)

We defined a OpenVINO™ transformation "InsertSlice" to find the logits (Results) node via ov::pass::MatchPass, then search along root->parent->grandparent node to find the Reshape node. Afterward, we insert a Slice node between the Reshape and Matmul nodes to extract the last element of seq_length with shape [1,1,4096]. In the end, we apply "InsertSlice" transformation to original OpenVINO™ model and save modified model on disk for deployment.

Modify model weights of specified layer in OpenVINO model

In case you want to update certain model layer weights after model training or fine-tuning/compression.

E.g. if you have an INT4 weight-compressed model using another model compression method, e.g. AWQ, you may want to transfer model weights optimized with the quantization method.

The most general method will be to convert the original model to OpenVINO™ model if the model direct conversion works. However, if first option is not works out of box, an alternative option is to replace the model weights from OpenVINO™ models with external fine-tuning model weights.

Figure 3: Update model weights of OpenVINO™ Model with external fine-tuned model weights

Here we introduce a common method to modify layer weights of Qwen model via OpenVINO™ transformation API.

As Figure 3 shows, the goal is to replace model weights and scale of the original Constant node with external fine-tuned weights and scale data.

At first, we use ov::pass::MatchPass method to find the Convert node after the target node. Then we create a new constant node with external weight saved as a numpy array. Please note, GPTQ int4 model weight is saved asuint4 (U4) binary format, while numpy can only represent data with numpy.uint8. Therefore, we use a help function to pack 2 uint4 binary data as 1 uint8 binary data. Then we replace the Convert input port from the original Constant node to the new Constant node.  Since the old constant node has no consumers and is neither the Result nor the Sink operation whose shared pointer counter is zero, the operation will be destructed and not be accessible anymore.

Here is a sample code to implement the workflow defined in Figure3 to replace Qwen Constant node via the new Constant node with external data:

# -*- coding: utf-8 -*-
import numpy as np
import openvino as ov
import torch 
from openvino.runtime import Core, Model, Type
from openvino.runtime.passes import Manager, GraphRewrite, MatcherPass, WrapType, Matcher
from openvino.runtime import opset10 as ops
from openvino.helpers import pack_data, unpack_data
pytorch_to_ov_layer_mapping = [{"__module.model.layers.0.mlp.down_proj/aten::to/Convert": }]
packed_layername_tensor_dict_list = [{"name":"__module.model.layers.0.mlp.down_proj/aten::to/Convert","value":np.ones([1376*4, 4096],dtype=np.uint8)}]

class InsertWeights(MatcherPass):
    def __init__(self,packed_layername_tensor_dict_list):
        self.model_changed = False

        param = WrapType("opset10.Convert")

        def callback(matcher: Matcher) -> bool:
            root = matcher.get_match_root()
            if root is None:
                return False
            root_output = matcher.get_match_value()
            for y in packed_layername_tensor_dict_list:
                #root_name = root.get_friendly_name().replace('.','_')
                root_name = root.get_friendly_name()
                print(f"root_name: {root_name}")
                if root_name.find(y["name"]) != -1 :
                    consumers = root.input_value(0).get_target_inputs()
                    unpacked_data = unpack_data(y["value"],Type.u4,y["value"].shape)
                    new_weights = ops.constant(np.zeros(root.get_output_shape(0)),Type.u4,name=y["name"]+"_new_const")
                    print("new_weights: ", new_weights)
          [:] = unpacked_data.ravel()
                    print(f"new_weights.shape: {new_weights.shape}")
                    for consumer in consumers:

                    # For testing purpose
                    self.model_changed = True
                    # Use new operation for additional matching

            return True

        self.register_matcher(Matcher(param,"InsertWeights"), callback)

if __name__ == "__main__":
    model_path = "Qwen1.5-7B-Chat-GPTQ-Int4-OV/pytorch/dldt/GPTQ_INT4-FP16/openvino_model.xml"
    modified_model_path = "Qwen1.5-7B-Chat-GPTQ-Int4-OV/pytorch/dldt/GPTQ_INT4-FP16/modified_openvino_model.xml")
    core = Core()
    ov_model = core.read_model(model_path)
    manager = Manager()
    ov.save_model(ov_model, modified_model_path)

We defined a OpenVINO™ transformation "InsertWeights" to find the target constant node via ov::pass::MatchPass, then we create a new Constat node with external numpy data and pack it as uint4 OpenVINO™ Tensor to replace original constant node in graph. In the end, we apply "InsertWeights" transformation to original OpenVINO™ model and save modified model on disk for deployment.


In this blog, we introduce how to apply graph customization based on OpenVINO™ model with OpenVINO™ transformation API. Furthermore, we show two examples of inserting layers & modifying layer weights based on Qwen LLM model with simple Python code.



OpenVINO™Transformation API

IntegrateOpenVINO™ with Your Application – Model Representation


Enable Textual Inversion with Stable Diffusion Pipeline via Optimum-Intel

August 15, 2023


Stable Diffusion (SD) is a state-of-the-art latent text-to-image diffusion model that generates photorealistic images from text. Recently, many fine-tuning technologies proposed to create custom Stable Diffusion pipelines for personalized image generation, such as Textual Inversion, Low-Rank Adaptation (LoRA). We’ve already published a blog for enabling LoRA with Stable Diffusion + ControlNet pipeline.

In this blog, we will focus on enabling pre-trained textual inversion with Stable Diffusion via Optimum-Intel. The feature is available in the latest Optimum-Intel, and documentation is available here.

Textual Inversion is a technique for capturing novel concepts from a small number of example images in a way that can later be used to control text-to-image pipelines. It does so by learning new “words” in the embedding space of the pipeline’s text encoder.

Figure1. Textual Inversion sample: injecting user-specific concepts into new scenes

As Figure 1 shows, you can teach new concepts to a model such as Stable Diffusion for personalized image generation using just 3-5 images.

Hugging Face Diffusers and Stable Diffusion Web UI provides useful tools and guides to train and save custom textual inversion embeddings. The pre-trained textual inversion embeddings are widely available in sd-concepts-library and civitai, which can be loaded for inference with the StableDiffusionPipeline using Pytorch as the runtime backend.

Here is an example to load pre-trained textual inversion embedding sd-concepts-library/cat-toy to inference with Pytorch backend.

from diffusers import StableDiffusionPipeline

model_id = "runwayml/stable-diffusion-v1-5"
pipe = StableDiffusionPipeline.from_pretrained(model_id)
prompt = "A <cat-toy> backpack"

image = pipe(prompt, num_inference_steps=50).images[0]"cat-backpack.png")

Optimum-Intel provides the interface between the Hugging Face Transformers and Diffusers libraries to leverage OpenVINOTM runtime to accelerate end-to-end pipelines on Intel architectures.

Figure2: Two approaches to enable textual inversion with Stable Diffusion

As Figure 2 shows that two approaches are available to enable textual inversion with Stable Diffusion via Optimum-Intel.

Although approach 1 seems quite straightforward and does not need any code modification in Optimum-Intel, the method requires the re-export ONNX model and then model conversion to the OpenVINOTM IR model whenever the SD baseline model is merged with anew textual inversion.

Instead, we propose approach 2 to support OVStableDiffusionPipelineBase to load pre-trained textual inversion embeddings in runtime to save disk storage while keeping flexibility.

  • Save disk storage: We only need to save an SD baseline model converted to OpenVINOTM IR (e.g.: SD-1.5 ~5GB) and multiple textual embeddings (~10KB-100KB), instead of multiple SD OpenVINOTM IR with textual inversion embeddings merged (~n *5GB), since disk storage is limited, especially for edge/client use case.
  • Flexibility: We can load (multiple) pre-trained textual inversion embeddings in the SD baseline model in runtime quickly, which supports the combination of embeddings and avoid messing up the baseline model.

How to enable textual inversion in runtime?

We implemented OVTextualInversionLoaderMixinbased on diffusers.loaders.TextualInversionLoaderMixin with the following features:

  • Load and parse textual embeddings saved as*.bin, *.pt, *.safetensors as a list of Tensors.
  • Update tokenizer for new “words” using new token id and expand vocabulary size.
  • Update text encoder embeddings via InsertTextEmbedding class based on OpenVINOTM ngraph transformation.

For the implementation details of OVTextualInversionLoaderMixin, please refer to here

Here is the sample code for InsertTextEmbedding class:

class InsertTextEmbedding(MatcherPass):
    OpenVINO ngraph transformation for inserting pre-trained texual inversion embedding to text encoder

    def __init__(self, token_ids_and_embeddings):
        self.model_changed = False
        param = WrapType("opset1.Constant")

        def callback(matcher: Matcher) -> bool:
            root = matcher.get_match_root()
            if root.get_friendly_name() == TEXTUAL_INVERSION_EMBEDDING_KEY:
                add_ti = root
                consumers = matcher.get_match_value().get_target_inputs()
                for token_id, embedding in token_ids_and_embeddings:
                    ti_weights = ops.constant(embedding, Type.f32, name=str(token_id))
                    ti_weights_unsqueeze = ops.unsqueeze(ti_weights, axes=0)
                    add_ti = ops.concat(
                        nodes=[add_ti, ti_weights_unsqueeze],

                for consumer in consumers:

                # Use new operation for additional matching

            # Root node wasn't replaced or changed
            return False

        self.register_matcher(Matcher(param, "InsertTextEmbedding"), callback)

InsertTextEmbeddingclass utilizes OpenVINOTM ngraph MatcherPass function to insert subgraph into the model. Please note, the MacherPass function can only filter layers by type, so we run two phases of filtering to find the layer that matched with the pre-defined key in the model:

  • Filter all Constant layers to trigger the callback function.
  • Filter layer name with pre-defined key “TEXTUAL_INVERSION_EMBEDDING_KEY” in the callback function

If the root name matched the pre-defined key, we will loop all parsed textual inversion embedding and token id pair and create a subgraph (Constant + Unsqueeze + Concat) by OpenVINOTM operation sets to insert into the text encoder model. In the end, we update the root output node with the last node in the subgraph.

Figure3. Overview of InsertTextEmbedding OpenVINOTM ngraph transformation

Figure 3 demonstrates the workflow of InsertTextEmbedding OpenVINOTM ngraph transformation. The left part shows the subgraph in SD 1.5 baseline text encoder model, where text embedding has a Constant node with shape [49408, 768], the 1st dimension is consistent with the original tokenizer (vocab size 49408), and the second dimension is feature length of each text embedding.

When we load (multiple) textual inversion, all textual inversion embeddings will be parsed as a list of tensors with shape[768], and each textual inversion constant will be unsqueezed and concatenated with original text embeddings. The right part is the result of applying InsertTextEmbedding ngraph transformation on the original text encoder, the green rectangle represents merged textual inversion subgraph.

Figure 4. 3 phase of SD 1.5 text encoder subgraph with single textual inversion visualized in Netron.

As Figure 4 shows, In the first phase, the original text embedding (marked as blue rectangle) is saved in Const node “text_model.embeddings.token_embedding.weight” with shape [49408,768], after InsertTextEmbedding ngraph transformation, new subgraph (marked as red rectangle) will be created in 2nd phase. In the 3rd phase, during model compilation, the new subgraph will be const folding into a single const node (marked as green rectangle) with a new shape [49409,768] by OpenVINOTM ConstantFolding transformation.

Stable Diffusion Textual Inversion Sample

Here are textual inversion examples verified with Stable Diffusion v1.5, Stable Diffusion v2.1 and Stable Diffusion XL 1.0 Base pipeline with latest optimum-intel

Setup Environment

conda create -n optimum-intel python=3.10
conda activate optimum-intel
python -m pip install "optimum-intel[openvino]"@git+
python -m pip install transformers, diffusers, safetensors
python -m pip install invisible-watermark>=0.2.0

Run SD 1.5 + Cat-Toy Textual Inversion Example

from import OVStableDiffusionPipeline
import numpy as np

model_id = "runwayml/stable-diffusion-v1-5"
prompt = "A <cat-toy> back-pack"

# Run pipeline without textual inversion
pipe = OVStableDiffusionPipeline.from_pretrained(model_id, compile=False)
image1 = pipe(prompt, num_inference_steps=50).images[0]"sd_v1.5_without_cat_toy_ti.png")

# Run pipeline with textual inversion
pipe.load_textual_inversion("sd_concepts/cat-toy", "<cat-toy>")
image2 = pipe(prompt, num_inference_steps=50).images[0]"sd_v1.5_with_cat_toy_ti.png")
Figure 5. The left image shows the generation result of SD 1.5 baseline, while the right image shows the generation result of SD 1.5 baseline + Cat-Toy textual inversion.

Run SD 2.1 + Midjourney 2.0 Textual Inversion Example

from import OVStableDiffusionPipeline
import numpy as np

model_id = "stabilityai/stable-diffusion-2-1"
prompt = "A <midjourney> style photo of an astronaut riding a horse on mars"

# Run pipeline without midjourney textual inversion
pipe = OVStableDiffusionPipeline.from_pretrained(model_id, compile=False, cache_dir=None)
image1 = pipe(prompt, num_inference_steps=50).images[0]"sd_v2.1_without_midjourney_ti.png")

# Run pipeline with midjourney textual inversion
pipe.load_textual_inversion("midjourney_sd_2_0", "<midjourney>")
image2 = pipe(prompt, num_inference_steps=50).images[0]"sd_v2.1_with_midjourney_ti.png")
Figure 6. The left image shows the generation result of SD 2.1 baseline, while the right image shows the generation result of SD 2.1 + Midjourney 2.0 textual inversion.

Run SDXL 1.0 Base + CharTurnerV2 Textual Inversion Example

from import OVStableDiffusionXLPipeline
import numpy as np

model_id = "stabilityai/stable-diffusion-xl-base-1.0"
prompt = "charturnerv2, multiple views of the same character in the same outfit, a character turnaround of a beautiful woman wearing a red jacket and black shirt, best quality, intricate details."

pipe = OVStableDiffusionXLPipeline.from_pretrained(model_id, export=False, compile=False, cache_dir=None)

# Run pipeline without textual inversion
image1 = pipe(prompt, num_inference_steps=50).images[0]"sdxl_base_1.0_without_charturnerv2_ti.png")

# Run pipeline with textual inversion
pipe.load_textual_inversion("./", "charturnerv2")
image2 = pipe(prompt, num_inference_steps=50).images[0]"sdxl_base_1.0_with_charturnerv2_ti.png")
Figure 7. The left image shows the generation result of SDXL 1.0 Base baseline, while the right image shows the generation result of SDXL 1.0 Base + CharTurnerV2 textual inversion.


In this blog, we proposed to load textual inversion embedding in the stable diffusion pipeline in runtime to save disk storage while keeping flexibility.

  • Implemented OVTextualInversionLoaderMixin to update tokenizer with additional token id and update text encoder with InsertTextEmbedding OpenVNO ngraph transformation.
  • Provides sample code to load textual inversion with SD 1.5, SD 2.1, and SDXL 1.0 Base and inference with Optimum-Intel


An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Optimum-Intel Text-to-Image with Textual Inversion

Hugging Face Textual Inversion


Enable LoRA weights with Stable Diffusion Controlnet Pipeline

August 7, 2023

Authors: Zhen Zhao(Fiona), Kunda Xu

Low-Rank Adaptation(LoRA) is a novel technique introduced to deal with the problem of fine-tuning Diffusers and Large Language Models (LLMs). In the case of Stable Diffusion fine-tuning, LoRA can be applied to the cross-attention layers for the image representations with the latent described.  You can refer HuggingFace diffusers to understand the basic concept and method for model fine-tuning:

In this blog, we aimed to introduce the method building up the pipeline for Stable Diffusion + ControlNet with OpenVINO™ optimization, and enable LoRA weights for Unet model of Stable Diffusion to generate images with different styles. The demo source code is based on:

Stable Diffusion ControlNet Pipeline

Step 1: Environment preparation

First, please follow below method to prepare your development environment, you can choose download model from HuggingFace for better runtime experience. In this case, we choose controlNet for canny image task.

$ mkdir ControlNet && cd ControlNet
$ wget

$ conda create -n SD python==3.10
$ conda activate SD

$ pip install opencv-contrib-python
$ pip install -q "diffusers>=0.14.0" "git+" controlnet-aux gradio
$ pip install openvino openvino-dev onnx
$ pip install torch==1.13.1 #important

$ git lfs install
$ git clone 
$ git clone
$ git clone 

$ wget 

* Please note, the diffusers start to use `torch.nn.functional.scaled_dot_product_attention` if your installed torch version is >= 2.0, and the ONNX does not support op conversion for “Aten:: scaled_dot_product_attention”. To avoid the error during the model conversion by “torch.onnx.export”, please make sure you are using torch==1.13.1.

Step 2: Model Conversion

The demo provides two programs, to convert model to OpenVINO™ IR, you should use “”. Please check the options of this script by:

$ python -h
usage: [-h] -b BATCH -sd SD_WEIGHTS [-lt LORA_TYPE] [-lw LORA_WEIGHTS]

  -h, --help            Show this help message and exit.
  -b BATCH, --batch BATCH
                        Required. batch_size for solving single/multiple prompt->image generation.
  -sd SD_WEIGHTS, --sd_weights SD_WEIGHTS
                        Specify the path of stable diffusion model
  -lt LORA_TYPE, --lora_type LORA_TYPE
                        Specify the type of lora weights, you can choose "safetensors" or "bin"
  -lw LORA_WEIGHTS, --lora_weights LORA_WEIGHTS
                        Add lora weights to Stable diffusion.

In this case, let us choose multiple batch size to generate multiple images. The common application of vison generation has two concepts of batch:

  1. `batch_size`: Specify the length of input prompt or negative prompt. This method is used for generating N images with N prompts.
  2. `num_images_per_prompt`: Specify the number of images that each prompt generates. This method is used to generate M images with 1 prompts.

Thus, for common user application, you can well use these two attributes in diffusers to generate N*M images by N prompts with increased random seed values. For example, if your basic seed is 42, to generate N(2)*M(2) images, the actual generation is like below:

  • N=1, M=1: prompt_list[0], seed=42
  • N=1, M=2: prompt_list[0], seed=43
  • N=2, M=1: prompt_list[1], seed=42
  • N=2, M=2: prompt_list[1], seed=43

In this case, let’s use N=2, M=1 as a quick example for demonstration, thus the use`--batch 2`. This script will generate static shape model by default. If you are using different value of N and M, please specify `--dynamic`.

$ python -b 2 -sd stable-diffusion-v1-5/

Please check your current path, make sure you already generated below models currently. Other ONNX files can be deleted for saving space.

  • controlnet-canny.<xml|bin>
  • text_encoder.<xml|bin>
  • unet_controlnet.<xml|bin>
  • vae_decoder.<xml|bin>

* If your local path already exists ONNX or IR model, the script will jump tore-generate ONNX/IR. If you updated the pytorch model or want to generate model with different shape, please remember to delete existed ONNX and IR models.

Step 3: Runtime pipeline test

The provided demo program `` is manually build-up the pipeline for StableDiffusionControlNet which refers to the original source of `diffusers.StableDiffusionControlNetPipeline`

The difference is we simplify the pipeline with 4 models’ inference by OpenVINO™ runtime API which can make sure the model inference can be accelerated on Intel® CPU and GPU platform.

The default iteration is 20, image shape is 512*512, seed is 42, and the input image and prompt is for “Girl with Pearl Earring”. You can adjust or custom your own pipeline attributes for testing.

$ python

In the case with batch_size=2, the generated image is like below:

Generated images with original Stable Diffusion v1.5 + canny ControlNet

Enable LoRA weights for Stable Diffusion

Normal LoRA weights has two types, one is ` pytorch_lora_weights.bin`,the other is using safetensors. In this case, we introduce both methods for these two LoRA weights.

The main idea for LoRA weights enabling, is to append weights onto the original Unet model of Stable Diffusion, then export IR model of Unet which remains LoRA weights.

There are various LoRA models on , we choose some public models on HuggingFace as an example, you can consider toreplace with your owns.

Step 4-1: Enable LoRA by pytorch_lora_weights.bin

This step introduces the method to add lora weights to Unet model of Stable Diffusion by `pipe.unet.load_attn_procs(...)` function. By using this way, the LoRA weights will be loaded into the attention layers of Unet model of Stable Diffusion.

$ git clone
$ rm unet_controlnet.* unet_controlnet/unet_controlnet.onnx
$ python -b 2 -sd stable-diffusion-v1-5/ -lt bin -lw finetune-lora-stable-diffusion/

* Remember to delete exist Unet model to generate the new IR with LoRA weights.

Then, run pipeline inference program to check results.

$ python

The LoRA weights appended Stable Diffusion model with controlNet pipeline can generate image like below:

Stable Diffusion v1.5+ LoRA bin weights + canny ControlNet

Step 4-2: Enable LoRA by safetensors typed weights

This step introduces the method to add LoRA weights to Stable diffusion Unet model by `diffusers/scripts/`. Diffusers provide the script to generate new Stable Diffusion model by enabling safetensors typed LoRA model. By this method, you will need to replace the weight path to new generated Stable Diffusion model with LoRA. You can adjust value of `alpha` option to change the merging ratio in `W = W0 + alpha * deltaW` for attention layers.

$ git clone
$ git clone && cd diffusers
$ python scripts/ --base_model_path ../stable-diffusion-v1-5/ --checkpoint_path ../fluffy-stable-diffusion-1.5-lora-trained-without-data/fluffySingleWordConcept_v10.safetensors --dump_path ../stable-diffusion-v1-5-fluffy-lora --alpha=1.5
$ cd .. && rm unet_controlnet.* unet_controlnet/unet_controlnet.onnx
$ python -b 2 -sd stable-diffusion-v1-5-fluffy-lora/ -lt safetensors

Then, run pipeline inference program to check results.

$ python

The LoRA weights appended SD model with controlnet pipeline can generate image like below:

Stable Diffusion v1.5 + LoRA safetensors weights + canny ControlNet

Step 4-3: Enable runtime LoRA merging by MatcherPass

This step introduces the method to add lora weights in runtime before Unet or text_encoder model compiling. It will be helpful to client application usage with multiple different LoRA weights to change the image style by reusing the same Unet/text_encoder structure.

This method is to extract lora weights in safetensors file and find the corresponding weights in Unet model and insert lora weights bias. The common method to add lora weights is like:

W = W0 + W_bias(alpha *, lora_down))

I intend to insert Add operation for Unet's attentions' weights by OpenVINO™ `opset10.add(W0,W_bias)`. The original attention weights in Unet model is loaded by `Const` op,  the common processing path is `Const->Convert->Matmul->...`, if we add the lora weights, we should insert the calculated lora weight bias as `Const->Convert->Add->Matmul->...`. In this function, we adopt `openvino.runtime.passes.MatcherPass` to insert `opset10.add()` with call_back() function iteratively.

Model transformation method of adding LoRA weights

Your own transformation operations will insert opset.Add() firstly, then during the model compiling with device. The graph will do constant folding to combine the Add operation with following MatMul operation to optimize the model runtime inference. Thus, this is an effective method to merge LoRA weights onto original model.

You can check with the implementation source code, and find out the definition of the MatcherPass function called `InsertLoRA(MatcherPass)`:

class InsertLoRA(MatcherPass):
    def __init__(self,lora_dict_list):
        self.model_changed = False

        param = WrapType("opset10.Convert")

        def callback(matcher: Matcher) -> bool:
            root = matcher.get_match_root()
            root_output = matcher.get_match_value()
            for y in lora_dict_list:
                if root.get_friendly_name().replace('.','_').replace('_weight','') == y["name"]:
                    consumers = root_output.get_target_inputs()
                    lora_weights = ops.constant(y["value"],Type.f32,name=y["name"])
                    add_lora = ops.add(root,lora_weights,auto_broadcast='numpy')
                    for consumer in consumers:

                    # Use new operation for additional matching

            # Root node wasn't replaced or changed
            return False

        self.register_matcher(Matcher(param,"InsertLoRA"), callback)

The `InsertLoRA(MatcherPass)` function will be registered by `manager.register_pass(InsertLoRA(lora_dict_list))`, and invoked by `manager.run_passes(ov_unet)`. After this runtime MatcherPass operation, the graph compile with device plugin and ready for inference.

Run pipeline inference program to check the results. The result is same as Step 4-2.

python -lp fluffy-stable-diffusion-1.5-lora-trained-without-data/fluffySingleWordConcept_v10.safetensors -a 1.5

The LoRA weights appended Stable Diffusion model with controlNet pipeline can generate image like below:

Stable Diffusion v1.5+runtime LoRA safetensors weights + ControlNet

Step 4-4: Enable multiple LoRA weights

There are many different methods to add multiple LoRA weights. I list two methods here. Assume you have two LoRA weigths, LoRA A and LoRA B. You can simply follow the Step 4-3 to loop the MatcherPass function to insert between original Unet Convert layer and Add layer of LoRA A. It's easy to implement. However, it is not good at performance.

Method 1: Loop InsertLoRA() twice

Please consider about the Logic of MatcherPass function. This fucntion required to filter out all layer with the Convert type, then through the condition judgement if each Convert layer connected by weights Constant has been fine-tuned and updated in LoRA weights file. The main costs of LoRA enabling is costed by InsertLoRA() function, thus the main idea is to just invoke InsertLoRA() function once, but append multiple LoRA files' weights.

Method 2: Append all LoRA weights together to insert

By above method to add multiple LoRA, the cost of appending 2 or more LoRA weights almost same as adding 1 LoRA weigths.

Now, let's change the Stable Diffusion with dreamlike-anime-1.0 to generate image with styles of animation. I pick two LoRA weights for SD 1.5 from

You probably need to do prompt engineering work to generate a useful prompt like below:

  • prompt: "1girl, cute, beautiful face, portrait, cloudy mountain, outdoors, trees, rock, river, (soul card:1.2), highly intricate details, realistic light, trending on cgsociety,neon details, ultra realistic details, global illumination, shadows, octane render, 8k, ultra sharp"
  • Negative prompt: "3d, cartoon, lowres, bad anatomy, bad hands, text, error"
  • Seed: 0
  • num_steps: 30
  • canny low_threshold: 100

$ python -lp soulcard.safetensors -a 0.7 -lp2 epi_noiseoffset2.safetensors -a2 0.7

You can get a wonderful image which generate an animated girl with soulcard typical border like below:

SD dreamlike-anime-1.0+canny_Controlnet+soulcard+noiseoffset

Additional Resources

Download OpenVINO™

OpenVINO™ Documentation

OpenVINO™ Notebooks

Provide Feedback & Report Issues

Notices & Disclaimers

Intel technologies may require enabled hardware, software, or service activation.

No product or component can be absolutely secure.

Your costs and results may vary.

Intel does not control or audit third-party data. You should consult other sources to evaluate accuracy.
Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

No license (express or implied, by estoppel or otherwise) to any intellectual property rights is granted by this document.

© Intel Corporation. Intel, the Intel logo, and other Intel marks are trademarks of Intel Corporation or its subsidiaries. Other names and brands may be claimed as the property of others.


Enable chatGLM by creating OpenVINO™ stateful model and runtime pipeline

July 3, 2023

Authors: Zhen Zhao(Fiona), Cheng Luo, Tingqian Li, Wenyi Zou


Since the Large Language Models (LLMs) become the hot topic, a lot Chinese language models have been developed and actively deployed in optimization platforms. chatGLM is one of the popular Chinese LLMs which are widely been evaluated. However, ChatGLM model is not yet a native model in Transformers, which means there remains support gap in official optimum. In this blog, we provide a quick workaround to re-construct the model structure by OpenVINO™ opset contains custom optimized nodes for chatGLM specifically and these nodes has been highly optimized by AMX intrinsic and MHA fusion.

*Please note, this blog only introduces a workaround of optimization method by creating OpenVINO™ stateful model for chatGLM.  This workaround has limitation of platform, which requires to use Intel® 4th Xeon Sapphire Rapids with AMX optimization. We do not promise the maintenance of this workaround.

Source link:

To support more LLMs, including llama, chatglm2, gpt-neox/dolly, gpt-j and falcon. You can refer this link which not limited on SPR platform, also can compute from Core to Xeon:

Source link:

ChatGLM model brief

If we check with original model source of chatGLM, we can find that the ChatGLM is not compatible with Optimum ModelForCasualML, it defines the new class ChatGLMForConditionalGeneration. This model has 3 main modules (embedding, GLMBlock layers and lm_logits) during the pipeline loop, the structure is like below:

Model structure of chatGLM

As you can see, the whole pipeline actually require model with two different graphs, the first-time inference with input prompt tokens do not require KV cache as inputs for GLMBlock layers. Since the second iteration, the previous results of QKV Attention should become the inputs of current round model inference. Along with the length of generated token increased, there will remain a lot of large sized memory copies between model inputs and outputs during pipeline inference.  We can use ChatGLM6b default model configurations as an example, the memory copies between input and output arrays are like below pseudocode:

while(eos_token_id || max_seq_len){
    memcpy(model_inp, model_outp, num_layer*2*sizeof(model_outp)* hidden_size)

Therefore, two topics is the most important:

  • How we can optimize model inference pipeline to eliminate memory copy between model inputs and outputs
  • How we can put optimization efforts on GLMBlock module by reinvent execution graph

Extremely optimization by OpenVINO™ stateful model

Firstly, we need to analyze the structure of GLMBlock layer, and try to encapsulate a class to invoke OpenVINO™ opset with below workflow. Then serialize the graph to IR model(.xml, .bin).

Build OpenVINO™ stateful model for chatGLM

To build an OpenVINO™ stateful model, you can refer to this document to learn.

OpenVINO™ also provide model creation sample to show how to build a model by opset.

It is clear to show that the emphasized optimization block is the custom op of Attention for chatGLM. The main idea is to build up a global context to store and update pastKV results internally, and then use intrinsic optimization for Rotary Embedding and Multi-Head Attentions. In this blog, we provide an optimized the attention structure of chatGLM with AMX intrinsic operators.

At the same time, we use int8 to compress the weights of the Fully Connected layer, you are not required to compress the model by Post Training Quantization (PTQ) or process with framework for Quantization Aware Training(QAT).

Create OpenVINO™ stateful model for chatGLM

Please prepare your hardware and software environment like below and follow the steps to optimize the chatGLM:

Hardware requirements

Intel® 4th Xeon platform(codename Sapphire Rapids) and above

Software Validation Environment

Ubuntu 22.04.1 LTS

python 3.10.11 for OpenVINO™ Runtime Python API

GCC 11.3.0 to build OpenVINO™ Runtime

cmake 3.26.4

Building OpenVINO™ Source

  • Install system dependency and setup environment
  • Create and enable python virtual environment

$ conda create -n ov_py310 python=3.10 -y
$ conda activate ov_py310

  • Install python dependency

$ pip install protobuf transformers==4.30.2 cpm_kernels torch>=2.0 sentencepiece pandas

  • Build OpenVINO™ with GCC 11.3.0
  • Clone OpenVINO™ and update submodule

$ git clone -b luocheng/chatglm_custom
$ cd openvino && git submodule update --init --recursive

  • Install python dependency for building python wheels

$ python -m pip install -U pip 
$ python -m pip install -r ./src/bindings/python/src/compatibility/openvino/requirements-dev.txt
$ python -m pip install -r ./src/bindings/python/wheel/requirements-dev.txt

  • Create build directory

$ mkdir build && cd build

  • Build OpenVINO™ with CMake

$ cmake .. -DENABLE_LLMDNN=ON \
    -DCMAKE_BUILD_TYPE=Release \
    -DCMAKE_INSTALL_PREFIX=`pwd`/install \
    -DCMAKE_INSTALL_RPATH=`pwd`/install/runtime/3rdparty/tbb/lib:`pwd`/install/runtime/3rdparty/hddl/lib:`pwd`/install/runtime/lib/intel64 \
$ make --jobs=$(nproc --all)
$ make install

  • Install built python wheel for OpenVINO™ runtime and openvino-dev tools

$ pip install ./install/tools/openvino*.whl

  • Check system gcc version and conda runtime gcc version. If the system gcc version is higher than conda gcc version like below, you should update conda gcc version for OpenVINO runtime. (Optional)

##check system (OpenVINO compiling env) gcc version
$ gcc --version
gcc (Ubuntu 11.3.0-1ubuntu1~22.04.1) 11.3.0

##check conda python (runtime env for OpenVINO later) gcc version
$ python
Python 3.10.11 (main, May 16 2023, 00:28:57) [GCC 11.2.0] on linux

##If sys gcc ver > conda gcc ver, upgrade conda gcc ver -> sys gcc ver
$ conda install -c conda-forge gcc=11.3.0

  • convert pytorch model to OpenVINO™ IR

$ cd ..
$ python tools/gpt/ /path/to/pytorch/model /path/to/ov/IR

Use OpenVINO Runtime API to build Inference pipeline for chatGLM  

We provide a demo by using transformers and OpenVINO™ runtime API to build the inference pipeline. In, we create a new class which inherit from transformers.PreTrainedModel. And we update the forward function by build up model inference pipeline with OpenVINO™ runtime Python API. Other member functions are migrated from ChatGLMForConditionalGeneration from, so that, we can make sure the input preparation work, set_random_seed, tokenizer/detokenizer and left pipelined operation can be totally same as original model source.

To enable the int8 weights compress, you just need a simple environment variable USE_INT8_WEIGHT=1. That is because during the model generation, we use int8 to compress the weights of the Fully Connected layer, and then it can use int8 weights to inference on runtime, you are not required to compress the model by framework or quantization tools.

Please follow below steps to test the chatGLM with OpenVINO™ runtime pipeline:

  • Run bf16 model

$ python3  tools/gpt/ /path/to/pytorch/model /path/to/ov/IR --use=ov

  • Run int8 model

$ USE_INT8_WEIGHT=1 python /path/to/pytorch/model /path/to/ov/IR --use=ov

Weights compression reduces memory bandwidth utilization to improve inference speed

We use VTune for performance comparison analysis of model weights bf16 and int8. Comparative analysis of memory bandwidth and CPI rate (Table 1). When model weight is compressed to int8, it can reduce memory bandwidth utilization and CPI rate.

Memory Bandwidth Utilization when model weight precision is bf16
Memory Bandwidth Utilization when model weight precision is int8
Table 1. CPI Rate for different model weight precision

Clockticks per Instructions Retired(CPI) event ratio, also known as Cycles per Instructions, is one of the basic performance metrics for the hardware event-based sampling collection, also known as Performance Monitoring Counter (PMC) analysis in the sampling mode. This ratio is calculated by dividing the number of unhalted processor cycles(Clockticks) by the number of instructions retired. On each processor the exact events used to count clockticks and instructions retired may be different, but VTune Profiler knows the correct ones to use.

A CPI < 1 is typical for instruction bound code, while a CPI > 1 may show up for a stall cycle bound application, also likely memory bound.


Along with the upgrading of OpenVINO™ main branch, the optimization work in this workaround will be generalized and integrated into official release. It will be helpful to scale more LLMs model usage. Please refer OpenVINO™ official release and Optimum-intel OpenVINO™ backend to get official and efficient support for LLMs.


AquilaChat-7B Language Model Enabling with Hugging Face Optimum Intel

July 3, 2023


What is AquilaChat-7B Language Model?

Figure 1: Aquila Language Model from BAAI

Aquila Language Model is a set of open-source large language models (LLMs) developed by the Beijing Academy of Artificial Intelligence (BAAI). Aquila models support both Chinese and English, commercial license agreements, and compliance with Chinese domestic data regulations.

AquilaChat-7B is a conversational language model that supports Chinese and English dialogue. It is based on the Aquila-7B foundation model and fine-tuned using supervised fine-tuning (SFT). AquilaChat-7B original Pytorch model and configurations are publicly available here.

Hugging Face Optimum Intel

Figure 2: Hugging Face Optimum Intel

Hugging Face is one of the most popular open-source data science and machine learning platforms. It acts as a hub for AI experts and enthusiasts—like a GitHub for AI. Over 200,000 models are available across Natural language processing, Multimodal models, Computer Vision, and Audio domains.

Hugging Face provides wide support for model optimization and deployment of open-sourced LLMs such as LLaMA, Bloom, GPT-Neox, Dolly 2.0, to name a few. More details please refer to Open LLM Leaderboard.

Optimum-Intel provides a simple interface between the Hugging Face and OpenVINOTM ecosystem to leverage high-performance inference capabilities for Intel architecture.  Here is a simple example to show how to run Dolly 2.0 models with OVModelForCausalLM using OpenVINOTM runtime.

from import OVModelForCausalLM
from transformers import AutoTokenizer

model_id = "databricks/dolly-v2-3b"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = OVModelForCausalLM.from_pretrained(model_id, export=True, use_cache=True)
prompt = "Deep learning is a type of machine learning"
inputs = tokenizer(prompt, return_tensors="pt")
output_ids = model.generate(**inputs)

Hola! So, for LLMs already supported by Hugging Face transformers and optimum, we can smoothly switch the model inference backend from Pytorch to OpenVINOTM by changing only two lines of code.

However, what if an LLM from an open-source community that not native supported by Hugging Face Transformers library? How can we still leverage the tools of Hugging Face and OpenVINOTM ecosystem for model optimization and deployment?

Indeed, AquilaChat-7B is a custom model for the Hugging Face Transformers. So, we use it as an example to elaborate the custom model enabling methodology step by step.

How to Enable a Custom Model on Hugging Face?

To leverage the Hugging Face ecosystem and optimization for AquilaChat-7B model, we need to convert the original Pytorch model to Hugging Face Format. Before we dive into conversion details, we need to figure out what is AquilaChat-7B’s model structure, tokenizer, and configurations.

According to Aquila’s official model description:

“The Aquila language model inherits the architectural design advantages of GPT-3 and LLaMA, replacing a batch of more efficient underlying operator implementations and redesigning the tokenizer for Chinese-English bilingual support. The Aquila language model is trained from scratch on high-quality Chinese and English corpora. “

Model Structure and Tokenizer

For model structure, Aquila Model adopts the original Meta LLaMA pytorch implementation, which combines RMSNorm (GPT-3) to improve training stability and Rotary Position Embedding (GPT-NeoX)to incorporate explicit relative position dependency in self-attention.

For tokenizer, instead of using byte-pair encoding (BPE) algorithms implemented by Sentence Piece, Aquila re-trained HuggingFace GPT-NeoX tokenizer with extended vocabulary (vocab_size =100008, including 8 special tokens, e.g. bos_token=100006, eos_token=100007, unk=0, pad=0 used for inference based on here.

Rotary Position Embedding

Rotary Position Embedding (RoPE) encodes the absolute position with a rotation matrix and meanwhile incorporates the explicit relative position dependency in the self-attention formulation. Compare to other position embedding methods, RoPE provides valuable properties such as flexibility of sequence length, long-term decay, and linear self-attention with relative position embedding. Based on the original paper, there are two mainstream implementations of RoPE:

As show in Figure 3, Meta LLaMA’s implementation directly use complex number to calculate rotary position embedding.

Figure 3. Meta LLaMA’s implementation of RoPE

As show in Figure 4, Google PaLM’s implementation expands the complex number operation and calculate sinusoidal functions in matrix equation of real numbers.

Figure 4.Google PaLM’s implementation of RoPE

Both RoPE implementations are valid for the Pytorch model. Hugging Face LLaMA implementation adopts PaLM’s RoPE implementation due to the limitation of complex type support for ONNX export.

Besides, Hugging Face provides a useful script to convert the original Meta LLaMA Pytorch Model to Hugging Face Format as follows:

  • Extract Pytorch weights and convert Meta LlaMA RoPE implementation to Hugging Face RoPE implementation.
  • Convert tokenizer.model trained with Sentence Piece to Hugging Face LLaMA tokenizer.

Convert AquilaChat-7B Model to Hugging Face Format

Similarly, we provide a to convert AquilaChat-7B Model to Hugging Face Format.

  • Extract Pytorch weights and convert Aquila RoPE implementation to Hugging Face RoPE implementation
  • Initialize and save a Hugging Face GPT-NeoX Tokenizer with extended vocabulary based on original tokenizer configurations provided by Aquila.
  • Add a to enable support forAutoModelForCausalLM and AutoTokenizer

Here is the converted Hugging Face version of AquilaChat-7B v0.6 model uploaded in Hugging Face.

You may convert pytorch weights to Hugging Face format in two steps:

  1. Download AquilaChat-7B Pytorch Model and configurations here
  2. Convert AquilaChat-7B Pytorch Model and configurations to Hugging Face Format
pip install transformers>=4.30.2
python --input_dir checkpoints/aquilachat-7b --model_size 7B --output_dir aquilachat-7b-hf

Hugging Face AquilaChat-7B Demo

Setup Environment

pip install optimum==1.8.8 optimum-intel[openvino]==1.9.1 onnx onnxruntime

Run inference with AutoModelForCausalLM

import torch
from transformers import AutoTokenizer, AutoModelForCausalLM
tokenizer = AutoTokenizer.from_pretrained('sammysun0711/aquilachat-7b-hf')
model = AutoModelForCausalLM.from_pretrained('sammysun0711/aquilachat-7b-hf', trust_remote_code=True)
model = model.eval()

question = '北京为什么是中国的首都?'
prompt = (
    '''A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.'''
    f'''###Human: {question}###Assistant:'''
with torch.no_grad():
    ret = model.generate(
        **tokenizer(prompt, return_tensors='pt').to('cpu'),

Run inference with OVModelForCausalLM

from transformers import AutoTokenizer
from import OVModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained('sammysun0711/aquilachat-7b-hf')
model = OVModelForCausalLM.from_pretrained('sammysun0711/aquilachat-7b-hf', export=True, use_cache=True, trust_remote_code=True)

question = '北京为什么是中国的首都?'
prompt = (
    '''A chat between a curious human and an artificial intelligence assistant. The assistant gives helpful, detailed, and polite answers to the human's questions.'''
    f'''###Human: {question}###Assistant:'''
ret = model.generate(
        **tokenizer(prompt, return_tensors='pt').to('cpu'),


In this blog, we show how to convert a custom Large Language Model (LLM) to Hugging Face format to leverage efficient optimization and deployment with Hugging Face and OpenVINOTM Ecosystem.

Please note, this is the initial model enabling step for AquilaChat-7B model with OpenVINOTM. We will continue to optimize performance along with upgrading OpenVINOTM for LLM scaling.  Please refer to OpenVINOTM and Optimum-Intel official release to get latest efficient support for LLMs with OpenVINOTM backend.