2 papers
cs.DC2026
DeltaLog: Deferred Materialization of Recurrent States for Linear Attention Decoding
Junqing Lin, Jingwei Sun, Guangzhong Sun
Linear attention models eliminate the quadratic prefix computation and context-growing KV cache of softmax attention by replacing pairwise token interactions with recurrent state u…
cs.DC2026
FlashQuant: Sparse-Dense Fusion for Memory-Efficient Outlier-Aware LLM Inference
Junqing Lin, Jingwei Sun, Zhengding Hu +1
Low-bit quantization reduces the memory footprint and computational cost of large language model (LLM) inference. However, high-magnitude outlier weights can induce substantial qua…