热点
"MagicDec" 相关文章
Together AI Optimizing High-Throughput Long-Context Inference with Speculative Decoding: Enhancing Model Performance through MagicDec and Adaptive Sequoia Trees
MarkTechPost@AI 2024-09-10T08:20:14.000000Z
MagicDec: Unlocking Up to 2x Speedup in LLaMA Models for Long-Context Applications
MarkTechPost@AI 2024-08-25T03:49:48.000000Z