Tag
PagedAttention
Every PagedAttention story we've curated in Bowl of Data, newest issue first — part of our weekly digest across AI, security, blockchain, and engineering.
Week 44 · 2026
Read the issue-
TAO: Tool-Aware Joint Scheduling for LLM-Based Agentic Serving
This technical paper presents TAO, a new scheduling approach for LLM-based agents that optimizes both tool availability and KV cache utilization. By integrating tool timing into the admission and placement process, TAO improves the efficiency of agentic workflows.
Week 37 · 2026
Read the issue-
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
This technical report examines the efficacy of using Random Attention for KV cache eviction to optimize LLM inference throughput. The study shows that this method significantly boosts tokens per second in high-concurrency scenarios without sacrificing model accuracy.
Week 36 · 2026
Read the issue-
Random Attention: Rethinking KV Cache Eviction for Efficient Reasoning
This technical report examines the efficacy of using Random Attention for KV cache eviction to optimize LLM inference throughput. The study shows that this method significantly boosts tokens per second in high-concurrency scenarios without sacrificing model accuracy.
Free weekly digest
Get next Saturday’s issue in your inbox
The week’s most relevant AI, security, blockchain, and engineering stories — curated, summarised, and reviewed by humans. No spam, unsubscribe anytime.
Subscribe — it’s free