thu-ml/SageAttention

by thu-ml · Video Generation · updated 7mo ago

[ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-to-end metrics across language, image, and video models.

More in Video Generation

waoowaoo

waooAI

08

Video Generation

首家工业级全流程 AI 影视生产平台。Industry-first professional AI Agent platform for controllable film & v

Sana

NVlabs

11

Video Generation

SANA: Efficient High-Resolution Image Synthesis with Linear Diffusion Transformer

vllm-omni

vllm-project

17

Video Generation

A framework for efficient model inference with omni-modality models

ViMax

HKUDS

22

Video Generation

"ViMax: Agentic Video Generation (Director, Screenwriter, Producer, and Video Generator Al