2 citations · 3 across the 9 of their papers we have counts for
5 papers · 1 filter
Epoch: Compiling Diffusion Blocks for Sparse MoE Serving
Jianian Zhu, Hang Wu, Yinghui Li +3
Diffusion language models generate text by refining a fixed-size block of token positions through many forward passes, a loop that does not match the per-forward execution unit use…
Odin: Primitive-Level Synchronization for Distributed Point-Based Neural Rendering
Zhenxiang Ma, Zeyu He, Yuanzhen Zhou +6
Point-based neural rendering (PBNR) represents 3D scenes as explicit, trainable primitives and underpins high-quality reconstruction and emerging embodied AI and world-model pipeli…
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…
Jenga: Effective Memory Management for Serving LLM with Heterogeneity
Chen Zhang, Kuntai Du, Shu Liu +10
Large language models (LLMs) are widely used but expensive to run, especially as inference workloads grow. To lower costs, maximizing the request batch size by managing GPU memory…
FastDecode: High-Throughput GPU-Efficient LLM Serving using Heterogeneous Pipelines
Jiaao He, Jidong Zhai
Cost of serving large language models (LLM) is high, but the expensive and scarce GPUs are poorly efficient when generating tokens sequentially, unless the batch of sequences is en…