collaborators

5 papers

cs.CL2025

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…

cs.CL2025

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…

cs.CL2025

PanGu- Pro:Rethinking Optimization and Architecture for Tiny Language Models

Yehui Tang, Kai Han, Fangcheng Liu +7

The power of large language models (LLMs) has been demonstrated through numerous data and computing resources. However, the application of language models on mobile devices is faci…

cs.CL2024

EMS-SD: Efficient Multi-sample Speculative Decoding for Accelerating Large Language Models

Yunsheng Ni, Chuanjian Liu, Yehui Tang +2

Speculative decoding emerges as a pivotal technique for enhancing the inference speed of Large Language Models (LLMs). Despite recent research aiming to improve prediction efficien…

cs.CL2024

Kangaroo: Lossless Self-Speculative Decoding via Double Early Exiting

Fangcheng Liu, Yehui Tang, Zhenhua Liu +3

Speculative decoding has demonstrated its effectiveness in accelerating the inference of large language models while maintaining a consistent sampling distribution. However, the co…