8 papers
Bidirectional Resource Scheduling for Disaggregated and Asynchronous RL Post-Training
Tan Zhiqiang, Zhiqiang Tan, Maoxin Wang +11
It is well established that the reasoning capabilities of large language models (LLMs) can be improved by applying reinforcement learning (RL) in a post-training stage. In a standa…
Position: LLM Inference Should Be Evaluated as Energy-to-Token Production
Xiang Liu, Shimiao Yuan, Zhenheng Tang +5
LLM inference is still evaluated mainly as a model or software problem: accuracy, latency, throughput, and hardware utilization. This is incomplete. At deployment scale, the releva…
Dissecting the NVIDIA Hopper Architecture through Microbenchmarking and Multiple Level Analysis
Weile Luo, Ruibo Fan, Zeyu Li +4
This study presents a comprehensive multi-level analysis of the NVIDIA Hopper GPU architecture, focusing on its performance characteristics and novel features. We benchmark Hopper'…
RA-NeRF: Robust Neural Radiance Field Reconstruction with Accurate Camera Pose Estimation under Complex Trajectories
Qingsong Yan, Qiang Wang, Kaiyong Zhao +4
Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have emerged as powerful tools for 3D reconstruction and SLAM tasks. However, their performance depends heavily on ac…
BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems
Yuxin Wang, Yuhan Chen, Zeyu Li +11
Serving systems for Large Language Models (LLMs) are often optimized to improve quality of service (QoS) and throughput. However, due to the lack of open-source LLM serving workloa…
SphereFusion: Efficient Panorama Depth Estimation via Gated Fusion
Qingsong Yan, Qiang Wang, Kaiyong Zhao +4
Due to the rapid development of panorama cameras, the task of estimating panorama depth has attracted significant attention from the computer vision community, especially in applic…