9 papers
FOCUS: FP4 Optimization via Coupled-Relaxation and Dual-Granularity Scaling
Xianglong Yan, Hong Liu, Chengzhu Bao +4
Large language models (LLMs) achieve remarkable performance but are expensive to deploy due to their enormous size. FP4 quantization, with formats such as MXFP4 and NVFP4, offers a…
LongCat Sparse Attention: Taming the Lightning via Streaming-aware Hierarchical Cross-Layer Indexing
Wen Zan, Jiaqi Zhang, Jianchao Tan +11
DeepSeek Sparse Attention (DSA) enables efficient long-context modeling through its Lightning Indexer. However, practical deployment remains constrained by the indexer's expensive…
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…