Understand this story
The English summary is being updated. See the reporting timeline below.
Latest development · Report
RecSA Extrapolates a 32K-Trained Model to 2M Tokens 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
RecSA Extrapolates a 32K-Trained Model to 2M Tokens at Logarithmic Cost
UCSD Hao AI Lab introduced RecSA, which builds a tree over the KV cache and searches it level by level, making the cost of each query scale as O(log L) and extrapolating Qwen3-4B, trained only on 32K contexts, to 2M tokens. RecSA was trained on 0.62B tokens and outperformed the baselines across RULER context lengths from 131K to 2M, scoring 60.5 at 1M versus 40.0 for the strongest baseline, Dense + DCA. On a single H200, it delivered a 3.2× prefill speedup and a 3.8× decoding speedup at 524K. The code has been open-sourced and includes Triton and CUDA kernels, Qwen3 integration, RULER evaluation, and latency benchmarks.
AI Trends