Watermarking in vLLM
Watermarking in vLLM
摘要
How vLLM implements distribution-preserving Gumbel-max text watermarking with efficient GPU kernels, statistical detection, speculative decoding, and repeated-context safeguards.
How vLLM implements distribution-preserving Gumbel-max text watermarking with efficient GPU kernels, statistical detection, speculative decoding, and repeated-context safeguards.
译自 vLLM · 官方博客 · 录于 二〇二六年九月二十四日