# Co-Designing AI Models Using Speculative Decoding for Faster LLM Inference — retained record

> Retained news record from news:nvidia-developer-blog.

Canonical: https://highsignal.app/data/records/0b5680d25e861759

[← sources](https://highsignal.app/data)


source: [news](https://highsignal.app/data/news) (news:nvidia-developer-blog)  published 2026-09-02 16:04 ingested 2026-09-03 02:58

[original source ↗](https://developer.nvidia.com/blog/co-designing-ai-models-using-speculative-decoding-for-faster-llm-inference/)

## retained text

No document body was retained for this record — only its metadata was stored.

document fetched 2026-09-03 02:58 · canonical https://developer.nvidia.com/blog/co-designing-ai-models-using-speculative-decoding-for-faster-llm-inference