v1.12.1: Patch release

• Fix causal language models export by @eaidova in #477

v1.12.0: Weight only quantization, LCM, Pix2Struct , GPTBigCode

OpenVINO

Export CLI

• Add OpenVINO export CLI by @echarlaix in #437

optimum-cli export openvino --model gpt2 ov_model

New architectures

LCMs

• Enable Latent Consistency models OpenVINO export and inference by @echarlaix in #463

from optimum.intel import OVLatentConsistencyModelPipeline

pipe = OVLatentConsistencyModelPipeline.from_pretrained("SimianLuo/LCM_Dreamshaper_v7", export=True)
prompt = "sailing ship in storm by Leonardo da Vinci"
images = pipe(prompt=prompt, num_inference_steps=4, guidance_scale=8.0).images

Pix2Struct

• Add support for export and inference for pix2struct models by @eaidova in #450

GPTBigCode

• Add support for export and inference for GPTBigCode models by @echarlaix in #459

Changes and bugfixes

• Move VAE execution to fp32 precision on GPU by @eaidova in #432
• Enable OpenVINO export without ONNX export step by @eaidova in #397
• Enable 8-bit weight compression for OpenVINO model by @l-bat in #415
• Add image reshaping for statically reshaped OpenVINO SD models by @echarlaix in #428
• OpenVINO device updates by @helena-intel in #434
• Fix decoder model without cache by @echarlaix in #438
• Fix export by @echarlaix in #439
• Added 8 bit weights compression by default for decoders larger than 1B by @AlexKoff88 in #444
• Add fp16 and int8 conversion to OVModels and export CLI by @echarlaix in #443

model = OVModelForCausalLM.from_pretrained(model_id, load_in_8bit=True)

• Create default attention mask when needed but not provided by @eaidova in #457
• Do not automatically cache models when exporting a model in a temporary directory by @helena-intel in #462

Neural Compressor

• Integrate INC weight-only quantization by @mengniwang95 in #417
• Support num_key_value_heads by @jiqing-feng in #447
• Enable ORT model support to INC quantizer by @echarlaix in #436
• fix INC model loading by @echarlaix in #452
• Fix INC modeling by @echarlaix in #453
• Add starcode past-kv shape for TSModelForCausal class by @changwangss in #371
• Fix transformers v4.35.0 compatibility by @echarlaix in #471
• Fix compatibility for optimum next release by @echarlaix in #460

Full Changelog: https://github.com/huggingface/optimum-intel/commits/v1.12.0

v1.11.1: Patch release

• Fix compatibility with optimum by @echarlaix in b4663b4

Full Changelog: v1.11.0...v1.11.1

v1.11.0: MPT, TIMM models, VAE image processor

OpenVINO

• Fix SDXL model U-NET component static reshaping by @eaidova in #390
• Allow changing pkv precision by @AlexKoff88 in #393
• Removed pkv history from quantization statistics of decoders by @AlexKoff88 in #394
• Add audio tasks for OpenVINO inference by @helena-intel in #396
• Do not download ONNX model in SD pipeline if not needed by @eaidova in #402
• Enable loading of Text Inversion at runtime for OpenVINO SD pipelines by @sammysun0711 in #400
• Enable Timm models OpenVINO export and inference @sawradip in #404
• Fix OpenVINO Timm models loading by @echarlaix in #413
• Add VAE image processor by @echarlaix in #421
• Enable MPT OpenVINO export and inference by @echarlaix in #425

Neural Compressor

• Fixed ONNX export for neural-compressor>=2.2.2 by @PenghuiCheng in #409
• Enable ONNX export for INC PTQ model by @echarlaix in #373
• Fix INC CLI by @echarlaix in #426

Full Changelog: https://github.com/huggingface/optimum-intel/commits/v1.11.0

v1.10.1: Patch release

• Set minimum optimum version by @echarlaix in #382
• Fix compilation step so that it can be performed before inference by @echarlaix in #384

v1.10.0: Stable Diffusion XL pipelines

Stable Diffusion XL

Enable SD XL OpenVINO export and inference for text-to-image and image-to-image tasks by @echarlaix in #377

from optimum.intel import OVStableDiffusionXLPipeline

model_id = "stabilityai/stable-diffusion-xl-base-0.9"
pipeline = OVStableDiffusionXLPipeline.from_pretrained(model_id, export=True)

prompt = "sailing ship in storm by Leonardo da Vinci"
image = pipeline(prompt).images[0]
pipeline.save_pretrained("openvino-sd-xl-base-0.9")

More examples in documentation

Full Changelog: v1.9.0...v1.10.0

v1.9.4: Patch release

• Fix OVDataLoader for NNCF quantization aware training for transformers > v4.31.0 by @echarlaix in #376

Full Changelog: v1.9.3...v1.9.4

v1.9.3: Patch release

• Improved performance of decoders by @AlexKoff88 #354
• Fix openvino model integration compatibility for optimum > v1.9.0 by @echarlaix in #365

Full Changelog: v1.9.2...v1.9.3

v1.9.2: Patch release

• Fix INC distillation to be compatible with neural-compressor v2.2.0 breaking changes by @echarlaix in #338

v1.9.1: Patch release

• Fix inference for OpenVINO export for causal language models by @echarlaix in #351