AHNU-2026级
计算机技术全日制专硕培养手账与重点速查
Blogs
AHNU-财务
教师科研经费报销流程与材料
Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads
用多个轻量预测头并行提出未来 token, 通过树状验证减少解码轮数
SpecInfer: Accelerating Large Language Model Serving with Tree-based Speculative Inference and Verification
用 token tree 并行验证多条推测路径以加速 LLM 服务
SpecTr: Fast Speculative Decoding via Optimal Transport
从最优传输理解投机解码及其多候选扩展
Fast Inference from Transformers via Speculative Decoding
用小模型猜测, 大模型并行验证, 且保持精确采样
SEQUOIA: Scalable and Robust Speculative Decoding
用动态规划优化 token tree, 以无放回采样提高验证鲁棒性
AHNU
Hello, AHNU!
Rethinking Generative Recommender Tokenizer: Recsys-Native Encoding and Semantic Quantization Beyond LLMs
从信息论角度剖析 SID 的设计理念