17 papers
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…
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…
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…
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…
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…
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…