2 papers
cs.CL2026
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…
cs.CL2026
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…