11 papers
DECO: Sparse Mixture-of-Experts with Dense-Comparable Performance on End-Side Devices
Chenyang Song, Weilin Zhao, Xu Han +3
While Mixture-of-Experts (MoE) scales model capacity without proportionally increasing computation, its massive total parameter footprint creates significant storage and memory-acc…
DashAttention: Differentiable and Adaptive Sparse Hierarchical Attention
Yuxiang Huang, Nuno M. T. Gonçalves, Federico Alvetreti +5
Current hierarchical attention methods, such as NSA and InfLLMv2, select the top-k relevant key-value (KV) blocks based on coarse attention scores and subsequently apply fine-grain…
AutoVecCoder: Teaching LLMs to Generate Explicitly Vectorized Code
Shangzhan Li, Xinyu Yin, Xuanyu Jin +8
Vectorization via Single Instruction, Multiple Data (SIMD) architectures is a cornerstone of high-performance computing. To fully exploit hardware potential, developers often resor…
Fitting Is Not Enough: Smoothness in Extremely Quantized LLMs
Yuzhuang Xu, Xu Han, Yuxuan Li +2
Large language models (LLMs) achieve strong performance but incur high deployment costs, motivating extremely low-bit but lossy quantization. Existing quantization algorithms mainl…
GAMMA: Global Bit Allocation for Mixed-Precision Models under Arbitrary Budgets
Zhangyang Yao, Haiyan Zhao, Haoyu Wang +1
Mixed-precision quantization improves the budget--accuracy trade-off for large language models (LLMs) by allocating more bits to sensitive modules. However, automating this allocat…
Seed3D 2.0: Advancing High-Fidelity Simulation-Ready 3D Content Generation
Diandian Gu, Jing Lin, Gaohong Liu +25
We present Seed3D 2.0, an advanced 3D content generation system built on Seed3D 1.0, with substantial improvements across generation fidelity, simulation-ready capabilities, and ap…
ArcLight: A Lightweight LLM Inference Architecture for Many-Core CPUs
Yuzhuang Xu, Xu Han, Yuxuan Li +1
Although existing frameworks for large language model (LLM) inference on CPUs are mature, they fail to fully exploit the computation potential of many-core CPU platforms. Many-core…
InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
Weilin Zhao, Zihan Zhou, Zhou Su +10
Long-sequence processing is a critical capability for modern large language models. However, the self-attention mechanism in the standard Transformer architecture faces severe comp…
CAMERA: Multi-Matrix Joint Compression for MoE Models via Micro-Expert Redundancy Analysis
Yuzhuang Xu, Xu Han, Yuanchi Zhang +5
Large Language Models (LLMs) with Mixture-of-Experts (MoE) architectures are distinguished by their strong performance scaling with increasing parameters across a wide range of tas…
Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design
Yudi Zhang, Weilin Zhao, Xu Han +4
Speculative decoding and quantization effectively accelerate memory-bound inference of large language models. Speculative decoding mitigates the memory bandwidth bottleneck by veri…
Hermes: Memory-Efficient Pipeline Inference for Large Models on Edge Devices
Xueyuan Han, Zinuo Cai, Yichu Zhang +4
The application of Transformer-based large models has achieved numerous success in recent years. However, the exponential growth in the parameters of large models introduces formid…