为 Transformers、Diffusers 等模型提供硬件加速与量化、ONNX 导出等优化工具，让推理和训练在各类硬件上跑得更快。
PyTorch 量化后端，接入 Optimum 生态，支持多种量化方案，帮你在推理和训练中压缩模型、降低显存占用。
把 Hugging Face 的 Transformers、Diffusers 等模型接到 Intel 的 OpenVINO 等优化工具上，加速 CPU/GPU 推理，覆盖 LLM、语音识别、语音合成和多模态模型。
面向大模型量化的压缩工具包，支持 NVIDIA、AMD、Intel、华为昇腾等多硬件加速，可无缝接入 HF、vLLM 和 SGLang 推理。
… Gemma 3n ([ 1650](https://github.com/huggingface/optimum-intel/pull/1650) by @anatyrova) - Qwen3-Omni-MOE ([ 1700](https://github.com/huggingface/optimum-intel/pull/1700
…lyasMoutawwakil in https://github.com/huggingface/optimum/pull/2395 Remove deprecated INC and IPEX from documentation by @echarlaix in https://github.com/huggingface/opti
…a2 by @rkazants in https://github.com/huggingface/optimum-intel/pull/1354 Add OpenVINO support for BitNet by @rkazants in https://github.com/huggingface/optimum-intel/pul
…al breaking changes 1. ONNX integration moved to [Optimum ONNX](https://github.com/huggingface/optimum-onnx) ONNX export and ONNX Runtime inference related integrations w
…lyasMoutawwakil in https://github.com/huggingface/optimum/pull/2326 Batched inference support across all decoders by @IlyasMoutawwakil in https://github.com/huggingface/o
…els by @dacorvo in https://github.com/huggingface/optimum-quanto/pull/222 Rebuild extension when pytorch is updated by @dacorvo in https://github.com/huggingface/optimum-