paper-with-me

Papers

TorchAO: PyTorch-Native Training-to-Serving Model Optimization

2025-07-21 · Andrew Or, Apurva Jain, Daniel Vega-Myhre, Jesse Cai, Charles David Hernandez, Zhenrui Zheng, Driss Guessous, Vasiliy Kuznetsov, Christian Puhrsch, Mark Saroufim, Supriya Rao, Thien Tran, Aleksandar Samardžić arxiv

We present TorchAO, a PyTorch-native model optimization framework leveraging quantization and sparsity to provide an end-to-end, training-to-serving workflow for AI models. TorchAO supports a variety of popular model optimization techniques, including FP8 quantized training, quantization-aware training (QAT), post-training quantization (PTQ), and 2:4 sparsity, and leverages a novel tensor subclass abstraction to represent a variety of widely-used, backend agnostic low precision data types, including INT4, INT8, FP8, MXFP4, MXFP6, and MXFP8. TorchAO integrates closely with the broader ecosystem at each step of the model optimization pipeline, from pre-training (TorchTitan) to fine-tuning (TorchTune, Axolotl) to serving (HuggingFace, vLLM, SGLang, ExecuTorch), connecting an otherwise fragmented space in a single, unified workflow. TorchAO has enabled recent launches of the quantized Llama 3.2 1B/3B and LlamaGuard3-8B models and is open-source at https://github.com/pytorch/ao/.

📄 PDF Abstract BibTeX arXiv:2507.16099

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

torchtune: PyTorch native post-training library

2026-05-20 · Mark Obozov, Maxime Griot, Joseph Cummings, Evan Smothers 외 arxiv

Modern LLMs typically require multistage training pipelines to achieve strong downstream performance, with post-training serving as the main interface for adapting open-weight models. We introduce torchtune, a PyTorch-na…

MambaLite-Micro: Memory-Optimized Mamba Inference on MCUs

2025-09-05 · Hongjun Xu, Junxi Xia, Weisi Yang, Yueyuan Sui 외 arxiv

Deploying Mamba models on microcontrollers (MCUs) remains challenging due to limited memory, the lack of native operator support, and the absence of embedded-friendly toolchains. We present, to our knowledge, the first d…

Human Activity RecognitionKeyword Spotting

QPyTorch: A Low-Precision Arithmetic Simulation Framework

2019-10-09 · Tianyi Zhang, Zhiqiu Lin, Guandao Yang, Christopher De Sa

Low-precision training reduces computational cost and produces efficient models. Recent research in developing new low-precision training algorithms often relies on simulation to empirically evaluate the statistical effe…

Quantization

MCTensor: A High-Precision Deep Learning Library with Multi-Component Floating-Point

2022-07-18 · Tao Yu, Wentao Guo, Jianan Canal Li, Tiancheng Yuan 외

In this paper, we introduce MCTensor, a library based on PyTorch for providing general-purpose and high-precision arithmetic for DL training. MCTensor is used in the same way as PyTorch Tensor: we implement multiple basi…

ExecuTorch -- A Unified PyTorch Solution to Run AI Models On-Device

2026-05-05 · Mergen Nachin, Digant Desai, Sicheng Stephen Jia, Chen Lai 외 arxiv

Local execution of AI on edge devices is important for low latency and offline operation. However, deploying models on diverse hardware remains fragmented, often requiring model conversion or complete reimplementation ou…