Poster by Pengle Zhang Papers
2 papers found
Conference
SageAttention2: Efficient Attention with Thorough Outlier Smoothing and Per-thread INT4 Quantization
Jintao Zhang, Haofeng Huang, Pengle Zhang et al.
ICML 2025arXiv:2411.10958
66
citations
SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration
Jintao Zhang, Jia wei, Pengle Zhang et al.
ICLR 2025arXiv:2410.02367
95
citations