cd /news/artificial-intelligence/cosa-accelerating-long-context-infer… · home topics artificial-intelligence article
[ARTICLE · art-78063] src=arxiv.org ↗ pub= topic=artificial-intelligence verified=true sentiment=↑ positive

CoSA: Accelerating Long-Context Inference via Proxy-Kernel Co-Designed Sparse Attention

Researchers propose CoSA, a training-free sparse attention method that couples a Kernel-Aware Proxy with an Ordered-Skipping Kernel to accelerate long-context inference. CoSA achieves a 4.93× attention speedup and reduces end-to-end Time-to-First-Token by 2.53× at 128K context length with negligible performance degradation.

read1 min views1 publishedJul 29, 2026

arXiv:2607.25291v1 Announce Type: new Abstract: 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 typically rely on a proxy to predict a binary sparse mask and a kernel to consume this mask and perform sparse attention computation. Such an approach is effective under moderate budgets. However, as the budget tightens, the estimated proxy inevitably drops some salient blocks, while the kernel can only apply the sparse mask mechanically, leading to an evident drop in model accuracy. We propose CoSA, a two-stage training-free Sparse Attention under proxy-kernel CO-design, which couples a Kernel-Aware Proxy (KAP) with an Ordered-Skipping Kernel (OSK). In the first stage, the KAP selects blocks under a moderate budget and produces an ordered mask that prescribes the order in which KV pages are visited in the kernel inner loop. In the second stage, the OSK applies this mask and skips more blocks under a tightened budget given online-softmax statistics. Across mainstream LLM backbones and long-context benchmarks, CoSA attains higher accuracy at lower budgets. Impressively, CoSA achieves a 4.93$\times$ attention speedup and reduces end-to-end Time-to-First-Token by 2.53$\times$ under a context length of 128K with negligible performance degradation.

── more in #artificial-intelligence 4 stories · sorted by recency
── more on @cosa 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/cosa-accelerating-lo…] indexed:0 read:1min 2026-07-29 ·