Quanto: a PyTorch quantization backend for Optimum
Hugging Face introduced Quanto, a new PyTorch-based quantization backend integrated into the Optimum library. Quanto supports multiple quantization schemes and data types, targeting efficient inference for large language models and other neural networks. The tool is designed to work across hardware backends and integrates with the Hugging Face ecosystem.
Related guides (3)
Related events (8)
Introducing Optimum: The Optimization Toolkit for Transformers at Scale
Hugging Face announced Optimum, an optimization toolkit designed to accelerate Transformers models on various hardware backends. The toolkit aims to bridge the gap between Transformers model development and hardware-specific optimizations from partners. It provides a unified interface for quantization, pruning, and hardware-accelerated inference across different accelerators.
Overview of Natively Supported Quantization Schemes in 🤗 Transformers
This Hugging Face blog post surveys the quantization methods natively integrated into the Transformers library as of September 2023, covering schemes such as GPTQ, bitsandbytes (LLM.int8, NF4), and related techniques. It explains how each method works, their trade-offs in terms of memory reduction and inference speed, and how practitioners can apply them via the Transformers API. The post serves as a practical reference for deploying large language models under memory constraints.
Accelerated Inference with Optimum and Transformers Pipelines
Hugging Face announced integration between the Optimum library and the Transformers Pipelines API, enabling hardware-accelerated inference with minimal code changes. The integration targets deployment on specialized hardware backends such as ONNX Runtime, allowing users to swap in optimized inference engines transparently. This lowers the barrier to production-grade inference optimization for practitioners using the Hugging Face ecosystem.
Optimum + ONNX Runtime: Faster Training for Hugging Face Models
Hugging Face's Optimum library integrates with Microsoft's ONNX Runtime Training to accelerate fine-tuning of transformer models. The integration aims to reduce training time and memory usage with minimal code changes for practitioners using the Hugging Face ecosystem. This tooling update targets enterprise and research users looking to optimize training efficiency on existing hardware.
Exploring Quantization Backends in Diffusers
Hugging Face published a technical overview of quantization backends available in the Diffusers library for image and video generation models. The post covers integration with multiple quantization frameworks (likely bitsandbytes, GGUF, torchao, and similar) and their trade-offs for diffusion model inference. It targets practitioners seeking to reduce memory footprint and improve throughput when deploying diffusion models.
Optimize and Deploy with Optimum-Intel and OpenVINO GenAI
Hugging Face's Optimum-Intel library integrates with Intel's OpenVINO runtime to enable optimized inference of generative AI models on Intel hardware. The post covers quantization, model export, and deployment workflows using OpenVINO GenAI APIs. This targets edge and CPU-based inference scenarios where reducing model size and latency is critical.
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
Hugging Face published a blog post detailing the integration of 4-bit quantization via bitsandbytes into the Transformers library, enabling large language models to run on consumer-grade hardware. The post covers NF4 (NormalFloat4) data type and double quantization techniques from the QLoRA paper, which together reduce memory footprint significantly while preserving model quality. It demonstrates how users can load models like LLaMA in 4-bit precision and fine-tune them using QLoRA with minimal code changes.
Optimum-NVIDIA: One-Line LLM Inference Acceleration via TensorRT-LLM
Hugging Face's Optimum-NVIDIA integration wraps NVIDIA's TensorRT-LLM backend to enable high-performance LLM inference with minimal code changes. The library targets developers who want near-peak GPU throughput without manually configuring TensorRT-LLM pipelines. It positions as a bridge between the Hugging Face ecosystem and NVIDIA's optimized inference stack.