{"articles":[{"slug":"this-is-called-speculative-decoding","title":"This is called Speculative Decoding","subtitle":null,"summary":"Gaurav Sen explains speculative decoding, the technique Google published in 2022 to make large language models answer 2 to 3 times faster with the same output: a small model drafts several tokens, the large model verifies the draft's prefixes in parallel, and the method now serves production traffic at Google and DeepSeek.","content_type":"tutorial","language":"en","canonical_url":"https://aiengg.dev/blog/this-is-called-speculative-decoding","author":{"name":"Gaurav Sen","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"AI Engg","url":"https://aiengg.dev/","listing_slug":null,"listing":null},"topics":[{"name":"AI Inference","slug":"ai-inference","url":"https://listedarticles.com/topics/ai-inference"},{"name":"Large Language Models","slug":"large-language-models","url":"https://listedarticles.com/topics/large-language-models"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":1435,"reading_minutes":6,"published_at":"2026-10-25T02:56:33.000Z","added_at":"2026-10-25T08:12:52.654Z","updated_at":"2026-10-25T08:12:52.654Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/this-is-called-speculative-decoding","markdown_url":"https://listedarticles.com/articles/this-is-called-speculative-decoding.md","example":false,"citation":"Gaurav Sen, AI Engg. \"This is called Speculative Decoding.\" 25 Oct 2026. https://aiengg.dev/blog/this-is-called-speculative-decoding (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://aiengg.dev/blog/this-is-called-speculative-decoding"},"snippet":null,"score":null}],"total":1,"count":1,"next_offset":null,"has_more":false,"query":{"q":null,"content_type":"tutorial","topic":"large-language-models","publisher":null,"about":null,"author":null,"language":null,"sort":"newest","limit":20,"offset":0}}