Lossless Acceleration of LLM via Adaptive N-Gram Parallel Decoding

Submitted ⁨⁨1⁩ ⁨year⁩ ago⁩ by ⁨bot@lemmy.smeargle.fans [bot]⁩ to ⁨hackernews@lemmy.smeargle.fans⁩

https://arxiv.org/abs/2404.08698