Running Stable Video Diffusion 2x Faster with OneDiff DeepCache NodeOneDiff ensuring almost lossless video quality and increasing iteration speed by more than 2x on A100.Dec 22, 2023Dec 22, 2023
Accelerating SDXL 3x Faster with DeepCache and OneDiffMake SDXL run 3.5x faster on RTX 3090 and 3x faster on A100.Dec 20, 2023Dec 20, 2023
Published inCodeXOneFlow v0.9.0 Came Out!This update contains 640 commits. For the full changelog, please check out: https://github.com/Oneflow-Inc/oneflow/releases/tag/v0.9.0.Feb 3, 2023Feb 3, 2023
Text to Image in less than 1 Second, Probably the Fastest Open Source Stable Diffusion EverOneFlow has refreshed the SOTA inference performance of Stable Diffusion. On A100 GPU, whether it is PCIe 40GB or SXM 80GB, OneFlow Stable…Dec 1, 20221Dec 1, 20221
Using Global Tensor to Program on Multi-Device Multi-GPU: Basic OperationsGlobal tensor can be executed on multi-device multi-GPU, and it’s an interface to implement the Global View programming.Aug 14, 2022Aug 14, 2022
OneEmbedding Allows Efficient Training of Large Recommender Models with Single GPUOneFlow team has recently released OneEmbedding, an efficient, extensible, and highly flexible recommender system component.Aug 11, 2022Aug 11, 2022
LiBai Model Library to Train Large Models More Easily and EfficientlyThe LiBai model library gathers the merits of mainstream Transformers libraries spanning Hugging Face, Megatron-LM, DeepSpeed,and FairSeq…Aug 9, 2022Aug 9, 2022
OneFlow v0.8.0 Came Out!We are thrilled to announce the release of OneFlow v0.8.0. This update contains 523 commits. For the full changlog, please check out…Aug 2, 2022Aug 2, 2022
Published inCodeXThe Journey of an Operator in a Deep Learning FrameworkWritten by Luyang Zhao; Translated by Wenwen Dong, Yanjun HuJun 24, 2022Jun 24, 2022