7 papers
HyDra: Demystifying and Taming Dynamic Context Parallelism at Production Scale
Zihao Fan, Yunzhuo Liu, Bo Jiang +4
Long-context training runs on sequences whose lengths span orders of magnitude, and dynamic context parallelism (DCP) gives each sequence its own CP degree. Existing DCP systems ei…
TOPIQ: Statistical Error Propagation for Quantity-of-Interest Prediction under Lossy Compression
Youyuan Liu, Bo Jiang, Taolue Yang +3
Lossy compression is essential for managing massive scientific data, but per-element error bounds do not translate into bounds on downstream quantities of interest (QoIs) such as r…
Error-bounded Point Cloud Compression Using Truncated Octahedron Quantization
Youyuan Liu, Longtao Zhang, Ruoyu Li +6
With the rapid advancement of large-scale scientific simulations, the massive volume of point cloud data generated has increasingly become a critical bottleneck for scientific stor…
3D Gaussian Splatting for Scientific Particle Data Compression and Rendering
Bo Jiang, Youyuan Liu, Taolue Yang +2
Large-scale particle simulations produce hundreds of millions of particles, straining storage, transfer, and interactive visualization. Existing lossy compressors such as SZ3 opera…
KVSculpt: KV Cache Compression as Distillation
Bo Jiang, Sian Jin
KV cache compression is critical for efficient long-context LLM inference. Approaches that reduce the per-pair footprint -- quantization and low-rank decomposition -- are orthogona…
PackKV: Reducing KV Cache Memory Footprint through LLM-Aware Lossy Compression
Bo Jiang, Taolue Yang, Youyuan Liu +3
Transformer-based large language models (LLMs) have demonstrated remarkable potential across a wide range of practical applications. However, long-context inference remains a signi…
KVComp: A High-Performance, LLM-Aware, Lossy Compression Framework for KV Cache
Bo Jiang, Taolue Yang, Youyuan Liu +3
Transformer-based large language models (LLMs) demonstrate impressive potential in various practical applications. However, long context inference poses a significant challenge due…