activity
20242026
collaborators

17 papers

cs.CL2026

PM-KVQ: Progressive Mixed-precision KV Cache Quantization for Long-CoT LLMs

Tengxuan Liu, Shiyao Li, Jiayi Yang +7

Recently, significant progress has been made in developing reasoning-capable Large Language Models (LLMs) through long Chain-of-Thought (CoT) techniques. However, this long-CoT rea…

cs.LG2025

STAlloc: Enhancing Memory Efficiency in Large-Scale Model Training with Spatio-Temporal Planning

Zixiao Huang, Junhao Hu, Hao Lin +9

The rapid scaling of large language models (LLMs) has significantly increased GPU memory pressure, which is further aggravated by training optimization techniques such as virtual p…

cs.LG2025

Mixture of Attention Spans: Optimizing LLM Inference Efficiency with Heterogeneous Sliding-Window Lengths

Tianyu Fu, Haofeng Huang, Xuefei Ning +10

Sliding-window attention offers a hardware-efficient solution to the memory and throughput challenges of Large Language Models (LLMs) in long-context scenarios. Existing methods ty…

cs.LG2025

BitSnap: Checkpoint Sparsification and Quantization in LLM Training

Yanxin Peng, Qingping Li, Baodong Wu +4

As large language models (LLMs) continue to grow in size and complexity, efficient checkpoint saving\&loading has become crucial for managing storage, memory usage, and fault toler…

cs.CL2025

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Tianyu Fu, Yi Ge, Yichen You +6

Large Language Models (LLMs) achieve impressive reasoning capabilities at the cost of substantial inference overhead, posing substantial deployment challenges. Although distilled S…

cs.LG2025

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

Enshu Liu, Qian Chen, Xuefei Ning +4

Image Auto-regressive (AR) models have emerged as a powerful paradigm of visual generative models. Despite their promising performance, they suffer from slow generation speed due t…