activity
20242026
collaborators

8 papers

cs.DC2026

UBEP: Re-architecting Expert Parallelism Communication Library for Production Superpods

Yipeng Liu, Chang Liu, Si Shen +16

The deployment of Mixture-of-Experts (MoE) models on production high-bandwidth superpods, such as NVIDIA's NVL72/576 and Huawei's CloudMatrix384, introduces critical challenges bey…

cs.CV2026

Rethinking Depth Pruning for Vision Transformers: A Heterogeneity-Aware Perspective

Zhenfeng Su, Kang Zhao, Han Bao +4

While prior studies have successfully compressed vision Transformers (ViTs) through various pruning techniques, most have concentrated on width pruning to achieve significant reduc…

cs.CL2026

BATQuant: Outlier-resilient MXFP4 Quantization via Learnable Block-wise Optimization

Ji-Fu Li, Manyi Zhang, Xiaobo Xia +4

Microscaling floating-point (MXFP) formats have emerged as a promising standard for deploying Multi-modal Large Language Models (MLLMs) and Large Language Models (LLMs) on modern a…

cs.CL2026

Unleashing Low-Bit Inference on Ascend NPUs: A Comprehensive Evaluation of HiFloat Formats

Pengxiang Zhao, Hui-Ling Zhen, Xing Li +10

As LLMs scale, low-bit floating-point formats like MXFP and NVFP4 offer new opportunities for precision and efficiency. In this work, we evaluate HiFloat (HiF8 and HiF4), a family…

cs.DC2025

HAP: Hybrid Adaptive Parallelism for Efficient Mixture-of-Experts Inference

Haoran Lin, Xianzhi Yu, Kang Zhao +7

Current inference systems for Mixture-of-Experts (MoE) models primarily employ static parallelization strategies. However, these static approaches cannot consistently achieve optim…

cs.CL2025

FlatQuant: Flatness Matters for LLM Quantization

Yuxuan Sun, Ruikang Liu, Haoli Bai +10

Recently, quantization has been widely used for the compression and acceleration of large language models (LLMs). Due to the outliers in LLMs, it is crucial to flatten weights and…