Understand this story
The English summary is being updated. See the reporting timeline below.
Latest development · Report
UCSD Hao AI Lab Releases RecSA, Enabling Million-Token Context Extrapolation at Logarithmic CostDevelopments
1 confirmed developments
- Source:UCSD Hao AI Lab
Reports and discussion timeline
Browse reports and discussion by time. Their evidence levels remain distinct.
Nov 19
UCSD Hao AI LabFirst-party
UCSD Hao AI Lab Releases RecSA, Enabling Million-Token Context Extrapolation at Logarithmic Cost
RecSA, proposed by UCSD Hao AI Lab, builds a tree structure over the KV cache, allowing the cost of each query to grow as O(log L) and enabling Qwen3-4B, trained only on 32K sequences, to extrapolate to 2M tokens. RecSA was trained on 0.62B tokens and outperformed the baselines on RULER at every length from 131K to 2M, scoring 60.5 at 1M versus 40.0 for the strongest baseline, Dense + DCA. On a single H200, RecSA accelerated prefill by 3.2× and decoding by 3.8× at 524K. The code has been open-sourced and includes Triton and CUDA kernels as well as evaluation implementations.
AI Trends