4 papers
Full-Pipeline Inference Optimization for MiMo-V2.5 Series: Pushing Hybrid SWA Efficiency to the Limit
Xiaomi MiMo Team, Anqi Liu, Aoxin Ma +28
We present a full-pipeline inference optimization for the MiMo-V2.5 model family, which combines Hybrid Sliding Window Attention (Hybrid SWA), sparse Mixture-of-Experts (MoE), and…
iFairy: the First 2-bit Complex LLM with All Parameters in
Feiyu Wang, Guoan Wang, Yihao Zhang +7
Quantization-Aware Training (QAT) integrates quantization into the training loop, enabling LLMs to learn robust low-bit representations, and is widely recognized as one of the most…
TinyR1-32B-Preview: Boosting Accuracy with Branch-Merge Distillation
Lin Sun, Guangxiang Zhao, Xiaoqi Jian +18
The challenge of reducing the size of Large Language Models (LLMs) while maintaining their performance has gained significant attention. However, existing methods, such as model di…
INT-FlashAttention: Enabling Flash Attention for INT8 Quantization
Shimao Chen, Zirui Liu, Zhiying Wu +6
As the foundation of large language models (LLMs), self-attention module faces the challenge of quadratic time and memory complexity with respect to sequence length. FlashAttention…