{"topic":{"slug":"ai-inference","name":"AI Inference","article_count":2,"latest_published_at":"2026-10-25T02:56:33.000Z","url":"https://listedarticles.com/topics/ai-inference"},"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},{"slug":"how-we-deploy-trillion-parameter-frontier-models-on-cerebras","title":"How we deploy trillion-parameter frontier models on Cerebras","subtitle":null,"summary":"Sarah Chieng explains how Cerebras splits a frontier model too large for one 44 GB WSE-3T wafer across many wafers, using the ~3T-parameter open model Kimi K3 as the example: fitting weights and request state in on-chip memory, mapping layers across chips as a pipeline, and serving many concurrent requests at 1000-2000+ tokens per second.","content_type":"blog_post","language":"en","canonical_url":"https://www.cerebras.ai/blog/how-we-deploy-trillion-parameter-frontier-models-on-cerebras","author":{"name":"Sarah Chieng","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Cerebras","url":"https://www.cerebras.ai/","listing_slug":"cerebras","listing":{"slug":"cerebras","name":"Cerebras","listing_type":"company","url":"https://listedstartups.com/companies/cerebras"}},"topics":[{"name":"AI Inference","slug":"ai-inference","url":"https://listedarticles.com/topics/ai-inference"},{"name":"AI Hardware","slug":"ai-hardware","url":"https://listedarticles.com/topics/ai-hardware"},{"name":"Large Language Models","slug":"large-language-models","url":"https://listedarticles.com/topics/large-language-models"},{"name":"Distributed Systems","slug":"distributed-systems","url":"https://listedarticles.com/topics/distributed-systems"}],"about_listings":[{"slug":"cerebras-inference","name":"Cerebras Inference","listing_type":"product","url":"https://listedstartups.com/products/cerebras-inference"}],"cover_image_url":null,"license":"all-rights-reserved","word_count":1185,"reading_minutes":5,"published_at":"2026-10-22T00:00:00.000Z","added_at":"2026-10-25T05:11:10.303Z","updated_at":"2026-10-25T05:11:10.303Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/how-we-deploy-trillion-parameter-frontier-models-on-cerebras","markdown_url":"https://listedarticles.com/articles/how-we-deploy-trillion-parameter-frontier-models-on-cerebras.md","example":false,"citation":"Sarah Chieng, Cerebras. \"How we deploy trillion-parameter frontier models on Cerebras.\" 22 Oct 2026. https://www.cerebras.ai/blog/how-we-deploy-trillion-parameter-frontier-models-on-cerebras (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.cerebras.ai/blog/how-we-deploy-trillion-parameter-frontier-models-on-cerebras"},"snippet":null,"score":null}],"total":2,"next_offset":null}