8 papers
CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention
Yufei Xue, Lin Niu, Hong Liu +6
The quadratic cost of self-attention makes long-context inference prohibitively expensive, and proxy-based block-sparse attention has become a practical remedy. Existing methods ty…
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…
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…
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…
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
Speculative decoding accelerates large language model (LLM) inference without compromising output quality. Recent parallel drafting methods further improve single-request performan…