SageAttention2 Technical Report: Accurate 4 Bit Attention for Plug-and-play Inference Acceleration
Paper • 2411.10958 • Published • 55 •
9
yunmorning
yunmorning
AI & ML interests
Training and serving large-scale AIs.
Recent Activity
liked a dataset 21 days ago
nebius/SWE-rebench-openhands-trajectories liked a model 2 months ago
zai-org/GLM-5.3 liked a model 4 months ago
moonshotai/Kimi-K3Organizations
