5 papers
SlimKV: Joint Token-Feature KV Cache Compression with Reconstruction-Free Beacon Attention
Zihan Teng, Jiayu Zhao, Wentao Ren +4
Long-context LLM serving is increasingly bottlenecked by KV-cache memory, especially in resource-constrained scenarios. Among existing KV-cache compression strategies, token-wise m…
BitsMoE: Cost-Aware Bit Allocation in Spectral Space for MoE LLM Quantization
Jiayu Zhao, Zihan Teng, Minhao Fan +4
Mixture-of-Experts (MoE) large language models incur substantial memory costs due to their large expert parameter counts. Mixed-precision quantization reduces these costs by alloca…
Observation of the in and
BESIII Collaboration, M. Ablikim, M. N. Achasov +769
Based on events collected with the BESIII detector, the and processes are stu…
Hardwired-Neurons Language Processing Units as General-Purpose Cognitive Substrates
Yang Liu, Yi Chen, Yongwei Zhao +24
The rapid advancement of Large Language Models (LLMs) has established language as a core general-purpose cognitive substrate, driving the demand for specialized Language Processing…
QiMeng: Fully Automated Hardware and Software Design for Processor Chip
Rui Zhang, Yuanbo Wen, Shuyao Cheng +17
Processor chip design technology serves as a key frontier driving breakthroughs in computer science and related fields. With the rapid advancement of information technology, conven…