按年被提到
20262026 · 2 次2026
大模型与语言模型›量化、解码与分词·arXiv:2603.03251 · cs.LG

Speculative Speculative Decoding

Tanishq Kumar, Tri Dao, Avner May · 2026
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2026-03-04 · 最近 2026-06-26
2不同的人
2活跃月份
2讨论串
1被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, and then verifying them in parallel with a single target model forward pass. However, speculative decoding itself relies on a sequential dependence between speculation and verification. We introduce speculative speculative decoding (SSD) to parallelize these operations. While a verification is ongoing, the draft model predicts likely verification outcomes and prepares speculations pre-emptively for them. If the actual verification outcome is then in the predicted set, a speculation can be returned immediately, eliminating drafting overhead entirely. We identify three key challenges presented by speculative speculative decoding, and suggest principled methods to solve each. The result is Saguaro, an optimized SSD algorithm. Our implementation is on average 30% faster than optimized speculative decoding baselines and up to 5x faster than autoregressive decoding with open source inference engines.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论anyg · 2026-06

“Not dumb at all. It's a whole field of active research - Speculative Decoding. A recent paper goes one level deeper with Speculative Speculative Decoding - https://arxiv.org/abs/2603.03251”

Overfitted a 900KB Transformer to Compress a 100MB CSV into 7MB原评论 ↗
被提交为 story · 1 次