150 citations · 310 across the 71 of their papers we have counts for
24 papers · 1 filter
ByteSplat: Efficient Distributed 3D Gaussian Splatting Training via Intra- and Inter-GPU communication reduction
Shuo Wu, He Zhu, Han Zhao +9
3D Gaussian Splatting (3DGS) enables photorealistic scene reconstruction, but training large-scale scenes requires substantial memory and computation. Distributing training across…
Weave: Fine-Grained Dynamic SM Scheduling in an MoE Megakernel for Compute-Communication Overlap
Ziyu Huang, Yangjie Zhou, Chenhao Zhu +15
Mixture-of-Experts (MoE) inference under expert parallelism (EP) turns each MoE layer into a distributed computation with costly dispatch and combine communication. State-of-the-ar…
GPU-Tile-Sim: A Tile-Centric GPU Simulation Framework for LLM Hardware-Software Co-Design
Yitong Ding, Jiawei Huang, Renyang Guan +7
Modern LLM (large language model) workloads increasingly rely on optimized GPU kernels through hardware-software co-design. These kernels achieve high-performance through fine-grai…
GF-DiT: Scheduling Parallelism for Diffusion Transformer Serving
Xinwei Qiang, Yifan Hu, Shixuan Sun +6
Diffusion Transformers (DiTs) have become the dominant architecture for image and video generation, creating growing demand for efficient DiT serving. Existing systems assign each…
InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models
Hongyu Chen, Letian Ruan, Zilin Xu +6
LoRA enables efficient customization of LLMs and is widely used in multi-tenant and multi-task serving. However, emerging model architectures such as MoE significantly increase LoR…
FlashFuser: Expanding the Scale of Kernel Fusion for Compute-Intensive Operators via Inter-Core Connection
Ziyu Huang, Yangjie Zhou, Zihan Liu +8
The scaling of computation throughput continues to outpace improvements in memory bandwidth, making many deep learning workloads memory-bound. Kernel fusion is a key technique to a…
ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive
Xinhao Luo, Zihan Liu, Yangjie Zhou +8
Large language model (LLM) decoding suffers from high latency due to fragmented execution across operators and heavy reliance on off-chip memory for data exchange and reduction. Th…
eLLM: Elastic Memory Management Framework for Efficient LLM Serving
Jiale Xu, Rui Zhang, Yi Xiong +11
Large Language Models are increasingly being deployed in datacenters. Serving these models requires careful memory management, as their memory usage includes static weights, dynami…
VQ-LLM: High-performance Code Generation for Vector Quantization Augmented LLM Inference
Zihan Liu, Xinhao Luo, Junxian Guo +11
In this work, we design and implement VQ-LLM, an efficient fused Vector Quantization (VQ) kernel generation framework. We first introduce a software abstraction called codebook cac…
Vortex: Efficient Sample-Free Dynamic Tensor Program Optimization via Hardware-aware Strategy Space Hierarchization
Yangjie Zhou, Honglin Zhu, Qian Qiu +9
Dynamic-shape deep neural networks (DNNs) are rapidly evolving, attracting attention for their ability to handle variable input sizes in real-time applications. However, existing c…
vTensor: Flexible Virtual Tensor Management for Efficient LLM Serving
Jiale Xu, Rui Zhang, Cong Guo +11
Large Language Models (LLMs) are widely used across various domains, processing millions of daily requests. This surge in demand poses significant challenges in optimizing throughp…
Towards Fast Setup and High Throughput of GPU Serverless Computing
Han Zhao, Weihao Cui, Quan Chen +6
Integrating GPUs into serverless computing platforms is crucial for improving efficiency. However, existing solutions for GPU-enabled serverless computing platforms face two signif…
Accelerating Sparse DNNs Based on Tiled GEMM
Cong Guo, Fengchen Xue, Jingwen Leng +5
Network pruning can reduce the computation cost of deep neural network (DNN) models. However, sparse models often produce randomly-distributed weights to maintain accuracy, leading…
GMLake: Efficient and Transparent GPU Memory Defragmentation for Large-scale DNN Training with Virtual Memory Stitching
Cong Guo, Rui Zhang, Jiale Xu +8
Large-scale deep neural networks (DNNs), such as large language models (LLMs), have revolutionized the artificial intelligence (AI) field and become increasingly popular. However,…
JUNO: Optimizing High-Dimensional Approximate Nearest Neighbour Search with Sparsity-Aware Algorithm and Ray-Tracing Core Mapping
Zihan Liu, Wentao Ni, Jingwen Leng +6
Approximate nearest neighbor (ANN) search is a widely applied technique in modern intelligent applications, such as recommendation systems and vector databases. Therefore, efficien…
DFlow: Efficient Dataflow-based Invocation Workflow Execution for Function-as-a-Service
Xiaoxiang Shi, Chao Li, Zijun Li +5
The Serverless Computing is becoming increasingly popular due to its ease of use and fine-grained billing. These features make it appealing for stateful application or serverless w…
DistSim: A performance model of large-scale hybrid distributed DNN training
Guandong Lu, Runzhe Chen, Yakai Wang +8
With the ever-increasing computational demand of DNN training workloads, distributed training has been widely adopted. A combination of data, model and pipeline parallelism strateg…
AdaptGear: Accelerating GNN Training via Adaptive Subgraph-Level Kernels on GPUs
Yangjie Zhou, Yaoxu Song, Jingwen Leng +7
Graph neural networks (GNNs) are powerful tools for exploring and learning from graph structures and features. As such, achieving high-performance execution for GNNs becomes crucia…
VELTAIR: Towards High-Performance Multi-tenant Deep Learning Services via Adaptive Compilation and Scheduling
Zihan Liu, Jingwen Leng, Zhihui Zhang +3
Deep learning (DL) models have achieved great success in many application domains. As such, many industrial companies such as Google and Facebook have acknowledged the importance o…
Characterizing and Demystifying the Implicit Convolution Algorithm on Commercial Matrix-Multiplication Accelerators
Yangjie Zhou, Mengtian Yang, Cong Guo +5
Many of today's deep neural network accelerators, e.g., Google's TPU and NVIDIA's tensor core, are built around accelerating the general matrix multiplication (i.e., GEMM). However…
DLFusion: An Auto-Tuning Compiler for Layer Fusion on Deep Neural Network Accelerator
Zihan Liu, Jingwen Leng, Quan Chen +4
Many hardware vendors have introduced specialized deep neural networks (DNN) accelerators owing to their superior performance and efficiency. As such, how to generate and optimize…
Accelerating Sparse DNN Models without Hardware-Support via Tile-Wise Sparsity
Cong Guo, Bo Yang Hsueh, Jingwen Leng +7
Network pruning can reduce the high computation cost of deep neural network (DNN) models. However, to maintain their accuracies, sparse models often carry randomly-distributed weig…
Towards QoS-Aware and Resource-Efficient GPU Microservices Based on Spatial Multitasking GPUs In Datacenters
Wei Zhang, Quan Chen, Kaihua Fu +6
While prior researches focus on CPU-based microservices, they are not applicable for GPU-based microservices due to the different contention patterns. It is challenging to optimize…
Balancing Efficiency and Flexibility for DNN Acceleration via Temporal GPU-Systolic Array Integration
Cong Guo, Yangjie Zhou, Jingwen Leng +6
The research interest in specialized hardware accelerators for deep neural networks (DNN) spikes recently owing to their superior performance and efficiency. However, today's DNN a…