RecSA 研究提出以对数成本将 32K 训练模型外推至 2M tokens
This project is done by our amazing @skywong265979 @Xinyu2ML @AlexZhang152005, and our advisor @haozhangml. The code is open source, including the kernels, the
AI 导读
UCSD Hao AI Lab 的 RecSA 在 KV cache 上构建树形结构,使每次查询成本按 O(log L) 增长,并让仅以 32K 训练的模型外推到 2M tokens。该方法从 Qwen3-4B 初始化、使用 0.62B tokens 训练,在 RULER 的 1M 测试中得分 60.5,强基线 Dense + DCA 为 40.0。在单张 H200 上,其 524K 预填充和解码分别加速 3.2×、3.8×;代码已开源,包含 kernels、Qwen3 集成、RULER 评测和延迟基准:https://t.co/qAFANlalhH
正文
This project is done by our amazing @skywong265979 @Xinyu2ML @AlexZhang152005, and our advisor @haozhangml. The code is open source, including the kernels, the Qwen3 integration, RULER evaluation and latency benchmarks.
Blog: https://t.co/yKpRitz8zw Paper: https://t.co/cWiIZS40Cy Code: https://t.co/qAFANlalhH
AI 热点