What's Changed

• Make sure they run when releasing by @IlyasMoutawwakil in #2395
• Remove deprecated INC and IPEX from documentation by @echarlaix in #2396
• Handle single-device models without hf_device_map after Transformers optimization by @ZX-ModelCloud in #2401
• docs: add empirical energy efficiency data to quantization concept guide by @hongping-zh in #2410
• Remove optimum-amd from documentation by @echarlaix in #2413
• Transformers v5 by @echarlaix in #2408
• 🔒 Pin GitHub Actions to commit SHAs by @paulinebm in #2418
• chore: bump doc-builder SHA for PR upload workflow by @rtrompier in #2422
• Fix gptqmodel backend check by @jiqing-feng in #2420
• fix gptq quantization condition by @jiqing-feng in #2416
• [CI] Bump style-bot SHA + switch to GitHub App by @paulinebm in #2435
• Remove deprecated IPEX pipelines by @echarlaix in #2429
• chore: enable Dependabot weekly GitHub Actions bumps by @hf-dependantbot-rollout[bot] in #2441
• bump to python 3.10 for workflows by @echarlaix in #2443
• Bump the actions group with 7 updates by @dependabot[bot] in #2442
• fix tests preprocessor loading by @echarlaix in #2445
• Add namespace when loading wikitext dataset by @echarlaix in #2446
• fix(exporters): handle read-only config in sentence-transformers >=5 by @SAY-5 in #2439

New Contributors

• @hongping-zh made their first contribution in #2410
• @paulinebm made their first contribution in #2418
• @rtrompier made their first contribution in #2422
• @hf-dependantbot-rollout[bot] made their first contribution in #2441
• @SAY-5 made their first contribution in #2439

Full Changelog: v2.1.0...v2.2.0

What's Changed

• handle missing TF2_WEIGHTS_NAME for newer transformers versions by @niyarrbarman in #2384
• Fully deprecate AutoGPTQ for GPT-QModel by @ZX-ModelCloud in #2385
• Transformers v5 pre release support by @IlyasMoutawwakil in #2387

New Contributors

• @ImadSaddik made their first contribution in #2375
• @niyarrbarman made their first contribution in #2384
• @ZX-ModelCloud made their first contribution in #2385

Full Changelog: v2.0.0...v2.1.0

Breaking changes since v1.x

v2.0.0 introduces several breaking changes

1. ONNX integration moved to Optimum ONNX

ONNX export and ONNX Runtime inference related integrations were moved to Optimum ONNX #2298

Installation

How to obtain the same behavior as v1.x

pip install "optimum-onnx[onnxruntime]"

or equivalently

pip install "optimum[onnxruntime]"

🚨 You shouldn't install optimum without an extra if you want to be able to export your model to ONNX, please follow the installation instructions from the documentation 🚨

ONNX Runtime Training

ONNX Runtime Training officially deprecated, more information on this in optimum-onnx v0.0.1 release notes

2. TF Lite export

TF Lite export officially deprecated #2340

3. BetterTransformer

BetterTransformer officially deprecated #2305

Improvements

Optimum pipelines

• Optimum pipelines by @IlyasMoutawwakil in #2343

General improvements

• Cleanup tasks manager by @IlyasMoutawwakil in #2346
• Remove legacy export by @IlyasMoutawwakil in #2359
• Native namespace packages (PEP 420) by @IlyasMoutawwakil in #2361
• Fix register loop by @IlyasMoutawwakil in #2364

New Contributors

• @openvino-dev-samples made their first contribution in #2335

Full Changelog: v1.27.0...v2.0.0

🚀 Major Upgrades

• Transformers v4.53 support and SmolLM3 model addition by @IlyasMoutawwakil in #2326
• Batched inference support across all decoders by @IlyasMoutawwakil in #2319
• VisualBert support by @Abdennacer-Badaoui in #2303

🔧 Enhancements & Fixes

• Fix taskmanager by @echarlaix in #2296
• Add task onnx register by @echarlaix in #2291
• ExporterConfig refactorization by @echarlaix in #2157
• remove timm from exporters extra by @echarlaix in #2299
• No more forcing separators by @IlyasMoutawwakil in #2279
• Fix broken Trainer documentation link in README by @VolodymyrBg in #2304
• Propagate library_name parameter in from_pretrained to export by @tomaarsen in #2328
• Fix 'Block pattern could not be match. Pass block_name_to_quantize argument in quantize_model' while loading Qwen VL GPTQ model by @arunmadhusud in #2295

🧹 Deprecations & v2

• Deprecated support for TFLite, BetterTransformer, and ONNXRuntime‑Training, these integrations will be fully removed in v2.
• TensorFlow models export will be removed in v2, consistent with Transformer library dropping TF/JAX support.
• ONNX and ONNXRuntime integrations will move into the new Optimum‑ONNX package.

New Contributors

• @dependabot[bot] made their first contribution in #2292
• @arunmadhusud made their first contribution in #2295
• @VolodymyrBg made their first contribution in #2304

Full Changelog: v1.26.1...v1.27.0

Add back from_transformers for base model by @echarlaix in #2288

ONNX export

• D-FINE support by @xenova in #2249
• ColPali support by @Balladie in #2251
• InternLM2 support by @gmf14 in #2244
• Chinese CLIP support by @xenova in #1591
• Qwen3 support by @IlyasMoutawwakil in #2278

New features & enhancements

• Add onnxslim support by @inisis in #2258
• Introduce ORTSessionMixin and enable general io binding by @IlyasMoutawwakil in #2234
• Fix and uniformize hub kwargs by @IlyasMoutawwakil in #2276
• Add compatibility with transformers 4.52 by @echarlaix in #2270
• Distribute and complete onnxruntime tests (decoder models) by @IlyasMoutawwakil in #2278
• Add ONNX Runtime optimization support for ModernBERT by @amas0 in #2208

New Contributors

• @inisis made their first contribution in #2258
• @Balladie made their first contribution in #2251
• @gmf14 made their first contribution in #2244
• @amas0 made their first contribution in #2208

• Fix ORT pipelines by @echarlaix in #2274

Full Changelog**: v1.25.2...v1.25.3

What's Changed

• Upgrade optimum-intel in setup extras by @echarlaix in #2271
• Match transformers behavior with return_dict by @IlyasMoutawwakil in #2269

Full Changelog: v1.25.1...v1.25.2

What's Changed

• Updated readme/pypi page by @IlyasMoutawwakil in #2268
• Fix bug ORTModelForFeatureExtraction by @Abdennacer-Badaoui in #2267
• Fix doc TPU section by @echarlaix in #2265

Full Changelog: v1.25.0...v1.25.1

🚀 New Features & Enhancements

• Add ONNX export support for ViTPose, RT-DETR, EfficientNet, Moonshine
• Infer if the model needs to be exported to ONNX during loading

  from optimum.onnxruntime import ORTModelForCausalLM

  model_id = "meta-llama/Llama-3.2-1B"
- model = ORTModelForCausalLM.from_pretrained(model_id, export=True)
+ model = ORTModelForCausalLM.from_pretrained(model_id)

• Transformers v4.49, v4.50 and v4.51 compatibility

👥 New Contributors

A huge thank you to our first-time contributors:

• @ruidazeng
• @ariG23498
• @janak2
• @qubvel
• @zhxchen17
• @xieofxie
• @EFord36
• @Thas-Tayapongsak
• @hans00
• @Abdennacer-Badaoui

What's Changed