Yehui Tang

PocketLLM: Ultimate Compression of Large Language Models via Meta Networks

Ye Tian, Chengcheng Wang, Jing Han +2

As Large Language Models (LLMs) continue to grow in size, storing and transmitting them on edge devices becomes increasingly challenging. Traditional methods like quantization and…

ScaleNet: Scaling up Pretrained Neural Networks with Incremental Parameters

Zhiwei Hao, Jianyuan Guo, Li Shen +4

Recent advancements in vision transformers (ViTs) have demonstrated that larger models often achieve superior performance. However, training these models remains computationally in…

LLM Data Selection and Utilization via Dynamic Bi-level Optimization

Yang Yu, Kai Han, Hang Zhou +4

While large-scale training data is fundamental for developing capable large language models (LLMs), strategically selecting high-quality data has emerged as a critical approach to…

EAQuant: Enhancing Post-Training Quantization for MoE Models via Expert-Aware Optimization

Zhongqian Fu, Tianyi Zhao, Ning Ding +4

Mixture-of-Experts (MoE) models enable scalable computation and performance in large-scale deep learning but face quantization challenges due to sparse expert activation and dynami…

Pangu Embedded: An Efficient Dual-system LLM Reasoner with Metacognition

Hanting Chen, Yasheng Wang, Kai Han +21

This work presents Pangu Embedded, an efficient Large Language Model (LLM) reasoner developed on Ascend Neural Processing Units (NPUs), featuring flexible fast and slow thinking ca…

SlimLLM: Accurate Structured Pruning for Large Language Models

Jialong Guo, Xinghao Chen, Yehui Tang +1

Large language models(LLMs) have garnered significant attention and demonstrated impressive capabilities in a wide range of applications. However, due to their enormous computation…

cs.CL2025★ 1 cited

Pangu Pro MoE: Mixture of Grouped Experts for Efficient Sparsity

Yehui Tang, Xiaosong Li, Fangcheng Liu +19

The surgence of Mixture of Experts (MoE) in Large Language Models promises a small price of execution cost for a much larger model parameter count and learning capacity, because on…

Pangu Light: Weight Re-Initialization for Pruning and Accelerating LLMs

Hanting Chen, Jiarui Qin, Jialong Guo +15

Large Language Models (LLMs) deliver state-of-the-art capabilities across numerous tasks, but their immense size and inference costs pose significant computational challenges for p…

Pangu Ultra MoE: How to Train Your Big MoE on Ascend NPUs

Yehui Tang, Yichun Yin, Yaoyuan Wang +71

Sparse large language models (LLMs) with Mixture of Experts (MoE) and close to a trillion parameters are dominating the realm of most capable language models. However, the massive…

Pangu Ultra: Pushing the Limits of Dense Large Language Models on Ascend NPUs

Yichun Yin, Wenyong Huang, Kaikai Song +49

We present Pangu Ultra, a Large Language Model (LLM) with 135 billion parameters and dense Transformer modules trained on Ascend Neural Processing Units (NPUs). Although the field…

Saliency-driven Dynamic Token Pruning for Large Language Models

Yao Tao, Yehui Tang, Yun Wang +3

Despite the recent success of large language models (LLMs), LLMs are particularly challenging in long-sequence inference scenarios due to the quadratic computational complexity of…

Post-Training Quantization for Diffusion Transformer via Hierarchical Timestep Grouping

Ning Ding, Jing Han, Yuchuan Tian +3

Diffusion Transformer (DiT) has now become the preferred choice for building image generation models due to its great generation capability. Unlike previous convolution-based UNet…

SpeCache: Speculative Key-Value Caching for Efficient Generation of LLMs

Shibo Jie, Yehui Tang, Kai Han +2

Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the…

Mixture of Lookup Experts

Shibo Jie, Yehui Tang, Kai Han +4

Mixture-of-Experts (MoE) activates only a subset of experts during inference, allowing the model to maintain low inference FLOPs and latency even as the parameter count scales up.…

Eve: Efficient Multimodal Vision Language Models with Elastic Visual Experts

Miao Rang, Zhenni Bi, Chuanjian Liu +3

Multimodal vision language models (VLMs) have made significant progress with the support of continuously increasing model sizes and data volumes. Running VLMs on edge devices has b…