27 июня 2026 г.

DSpark: Speculative decoding accelerates LLM inference [pdf]

rss:Hacker News: Front Page · оригинал

Article URL: https://github.com/deepseek-ai/DeepSpec/blob/main/DSpark_paper.pdf Comments URL: https://news.ycombinator.com/item?id=48696585 Points: 714 # Comments: 293

Заголовок: DSpark: Speculative decoding accelerates LLM inference [pdf]

Кратко: Article URL: https://github.com/deepseek-ai/DeepSpec/blob/main/DSpark_paper.pdf Comments URL: https://news.ycombinator.com/item?id=48696585 Points: 714 # Comments: 293

Детали: Article URL: https://github.com/deepseek-ai/DeepSpec/blob/main/DSpark_paper.pdf Comments URL: https://news.ycombinator.com/item?id=48696585 Points: 714 # Comments: 293