Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
Scout Before You Attend: Sketch-and-Walk Sparse Attention for Efficient LLM Inference
Hoang Anh Duy Le, Sahil Joshi, Zeyu Yang +2
Self-attention dominates the computational and memory cost of long-context LLM inference across both prefill and decode phases. To address this challenge, we introduce Sketch&Walk…
cs.LG2026
SOCKET: SOft Collision Kernel EsTimator for Sparse Attention
Sahil Joshi, Agniva Chowdhury, Wyatt Bellinger +5
Exploiting sparsity is key to efficient long-context inference, as attention dominates the cost of autoregressive decoding. Sparse attention reduces this cost by restricting comput…
cs.LG2025
RACE Attention: A Strictly Linear-Time Attention Layer for Training on Outrageously Large Contexts
Sahil Joshi, Agniva Chowdhury, Amar Kanakamedala +3
Softmax Attention has a quadratic time complexity in sequence length, which becomes prohibitive to run at long contexts, even with highly optimized GPU kernels. For example, FlashA…