From the 2 of 9 linked papers with an AI index.
4 papers · 1 filter
AngelSpec: Towards Real-World High Performance Inference with Speculative Decoding
Hong Liu, Rui Cen, Junhan Shi +10
Speculative decoding accelerates large language model inference without changing the target distribution, but no single drafting structure performs best across real-world workloads…
CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention
Yufei Xue, Lin Niu, Hong Liu +6
CoSA introduces a training-free, two-stage sparse attention method that jointly designs a proxy and kernel to efficiently handle very long contexts, achieving faster inference with…
PIVOT: Efficient Query-Group Indexing for Token-Level Sparse Attention
Hong Liu, Yuan Cheng, Lin Niu +5
Token-level sparse attention, as implemented by DeepSeek Sparse Attention (DSA) in production systems, makes the downstream attention efficient but shifts the bottleneck to the ind…
D-cut: Adaptive Verification Depth Pruning for Batched Speculative Decoding
Tianyu Liu, Yuhao Shen, Rui Cen +7
The paper introduces D-Cut, an adaptive method that prunes draft tokens across a batch to focus verification on the most promising tokens, improving the speed of speculative decodi…