Xu, Zhaozhuo

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

Liu, Z., Desai, A., Liao, F., Wang, W., Xie, V., Xu, Z., Kyrillidis, A., & Shrivastava, A. (2023) · arXiv

Advanced Neural Network ApplicationsTopic Modeling

Cited by 50

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

Liu, Z., Desai, A., Liao, F., Wang, W., Xie, V., Xu, Z., Kyrillidis, A., & Shrivastava, A. (2023) · Advances in Neural Information Processing Systems 36

Advanced Neural Network ApplicationsTopic Modeling

Cited by 50

LLM Multi-Agent Systems: Challenges and Open Problems

Han, S., Zhang, Q., Jin, W., & Xu, Z. (2024) · arXiv

Multi-Agent Systems and NegotiationDistributed Control Multi-Agent Systems

Cited by 33

KIVI : Plug-and-play 2bit KV Cache Quantization with Streaming Asymmetric Quantization

Liu, Z., Yuan, J., Jin, H., Zhong, S., Xu, Z., Braverman, V., Chen, B., & Hu, X. (2023) · Unpublished

Advanced Neural Network ApplicationsTopic Modeling

Cited by 6

KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization

Zhang, T., Yi, J., Xu, Z., & Shrivastava, A. (2024) · arXiv

Advanced Neural Network ApplicationsTopic Modeling

Cited by 1

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache

Liu, Z., Yuan, J., Jin, H., Zhong, S., Xu, Z., Braverman, V., Chen, B., & Hu, X. (2024) · arXiv

Advanced Neural Network ApplicationsParallel Computing and Optimization Techniques

Cited by 0