1 citations · 1 across the 7 of their papers we have counts for
9 papers
RPFQ-ViT: Rotated Phase-Frame Quantization for Extremely Low-Bit Weights in Vision Transformers
Mengyuan Fan, Bokai Huang, JiaMing Pan +4
Vision Transformers (ViTs) achieve strong performance on image recognition and mobile vision applications, but their high-dimensional linear projections and attention computations…
HAPMoE: Heterogeneity-Aware Automatic Parallelism Planning for Mixture-of-Experts Models Training
Mengyuan Fan, Peizhuang Cong, Zixiao Huang +7
As model sizes continue to scale, distributed training has become inevitable. Automatic parallelization techniques can derive efficient training parallelism strategies at low cost…
ConMoE: MoE Compression as Expert Selection and Functional Assignment
Yilun Yao, Jiaming Pan, Elsie Dai +4
Sparse Mixture-of-Experts (MoE) models scale model capacity through sparse activation, but storing their full parameters remains costly in GPU memory. Existing expert compression m…
Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in
Feiyu Wang, Xinyu Tan, Bokai Huang +4
Large language models (LLMs) have revolutionized artificial intelligence, yet their massive memory and computational demands necessitate aggressive quantization, increasingly pushi…
LPFQA: A Long-Tail Professional Forum-based Benchmark for LLM Evaluation
Liya Zhu, Peizhuang Cong, Jingzhe Ding +17
Large Language Models (LLMs) perform well on standard reasoning and question-answering benchmarks, yet such evaluations often fail to capture their ability to handle long-tail, exp…
Rank Also Matters: Hierarchical Configuration for Mixture of Adapter Experts in LLM Fine-Tuning
Peizhuang Cong, Wenpu Liu, Wenhan Yu +2
Large language models (LLMs) have demonstrated remarkable success across various tasks, accompanied by a continuous increase in their parameter size. Parameter-efficient fine-tunin…
BATON: Enhancing Batch-wise Inference Efficiency for Large Language Models via Dynamic Re-batching
Peizhuang Cong, Qizhi Chen, Haochen Zhao +1
The advanced capabilities of Large Language Models (LLMs) have inspired the development of various interactive web services or applications, such as ChatGPT, which offer query infe…
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…
Prediction Is All MoE Needs: Expert Load Distribution Goes from Fluctuating to Stabilizing
Peizhuang Cong, Aomufei Yuan, Shimao Chen +4
MoE facilitates the development of large models by making the computational complexity of the model no longer scale linearly with increasing parameters. The learning sparse gating…