5 papers
StreamKL: Fast and Memory-Efficient KL Divergence for Boosting Attention Distillation
Guangda Liu, Yiquan Wang, Chengwei Li +6
Attention distillation, which trains one attention distribution to match another by minimizing their Kullback-Leibler (KL) divergence, is widely used in knowledge distillation, mod…
LiveVLM: Efficient Online Video Understanding via Streaming-Oriented KV Cache and Retrieval
Zhenyu Ning, Guangda Liu, Qihao Jin +4
Recent developments in Video Large Language Models (Video LLMs) have enabled models to process hour-long videos and exhibit exceptional performance. Nonetheless, the Key-Value (KV)…
FreeKV: Boosting KV Cache Retrieval for Efficient LLM Inference
Guangda Liu, Chengwei Li, Zhenyu Ning +5
Large language models (LLMs) are widely deployed with rapidly expanding context windows to support increasingly demanding applications. However, long contexts pose significant depl…
ClusterKV: Manipulating LLM KV Cache in Semantic Space for Recallable Compression
Guangda Liu, Chengwei Li, Jieru Zhao +2
Large Language Models (LLMs) have been widely deployed in a variety of applications, and the context length is rapidly increasing to handle tasks such as long-document QA and compl…
STREAMINGGS: Voxel-Based Streaming 3D Gaussian Splatting with Memory Optimization and Architectural Support
Chenqi Zhang, Yu Feng, Jieru Zhao +4
3D Gaussian Splatting (3DGS) has gained popularity for its efficiency and sparse Gaussian-based representation. However, 3DGS struggles to meet the real-time requirement of 90 fram…