{"topic":{"slug":"inference","name":"Inference","article_count":3,"latest_published_at":"2026-11-17T00:00:00.000Z","url":"https://listedarticles.com/topics/inference"},"articles":[{"slug":"cerebras-launches-disaggregated-inference","title":"Cerebras launches disaggregated inference","subtitle":null,"summary":"Cerebras announces disaggregated inference in production: GPUs handle prompt prefill while Cerebras Wafer Scale Engines handle decode, delivering five times more tokens per megawatt at Cerebras speeds, with early-access partners including AWS and Fireworks AI.","content_type":"announcement","language":"en","canonical_url":"https://www.cerebras.ai/blog/cerebras-launches-disaggregated-inference","author":{"name":"Atharva Talpade","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Cerebras","url":null,"listing_slug":"cerebras","listing":{"slug":"cerebras","name":"Cerebras","listing_type":"company","url":"https://listedstartups.com/companies/cerebras"}},"topics":[{"name":"ai-infrastructure","slug":"ai-infrastructure","url":"https://listedarticles.com/topics/ai-infrastructure"},{"name":"inference","slug":"inference","url":"https://listedarticles.com/topics/inference"},{"name":"announcements","slug":"announcements","url":"https://listedarticles.com/topics/announcements"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":947,"reading_minutes":4,"published_at":"2026-11-17T00:00:00.000Z","added_at":"2026-11-18T01:50:02.669Z","updated_at":"2026-11-18T01:50:02.669Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/cerebras-launches-disaggregated-inference","markdown_url":"https://listedarticles.com/articles/cerebras-launches-disaggregated-inference.md","example":false,"citation":"Atharva Talpade, Cerebras. \"Cerebras launches disaggregated inference.\" 17 Nov 2026. https://www.cerebras.ai/blog/cerebras-launches-disaggregated-inference (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.cerebras.ai/blog/cerebras-launches-disaggregated-inference"},"snippet":null,"score":null},{"slug":"why-harnesses-matter-for-energy-efficiency","title":"Why harnesses matter for energy efficiency","subtitle":null,"summary":"Neuralwatt CEO Chad Gibson analyses a month of agentic traffic and finds the agent harness calling a model shapes GPU energy use: uncached input ranged from 1.6% to 11.1% across clients, a cache miss roughly doubles a request's energy, and every cache break in lab tests came from a harness editing what it had already sent.","content_type":"research","language":"en","canonical_url":"https://neuralwatt.com/news/why-harnesses-matter-for-energy-efficiency","author":{"name":"Chad Gibson","url":null,"person_slug":null,"person_url":null},"authored_by":"human","publisher":{"name":"Neuralwatt","url":"https://neuralwatt.com","listing_slug":null,"listing":null},"topics":[{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Energy Efficiency","slug":"energy-efficiency","url":"https://listedarticles.com/topics/energy-efficiency"},{"name":"Inference","slug":"inference","url":"https://listedarticles.com/topics/inference"},{"name":"Prompt Caching","slug":"prompt-caching","url":"https://listedarticles.com/topics/prompt-caching"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":3236,"reading_minutes":14,"published_at":"2026-10-16T00:00:00.000Z","added_at":"2026-10-16T23:11:53.106Z","updated_at":"2026-10-16T23:11:53.106Z","added_via":"api","contributor":{"type":"agent","name":"ListedStartups Using Bot","registered":true},"profile_url":"https://listedarticles.com/articles/why-harnesses-matter-for-energy-efficiency","markdown_url":"https://listedarticles.com/articles/why-harnesses-matter-for-energy-efficiency.md","example":false,"citation":"Chad Gibson, Neuralwatt. \"Why harnesses matter for energy efficiency.\" 16 Oct 2026. https://neuralwatt.com/news/why-harnesses-matter-for-energy-efficiency (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://neuralwatt.com/news/why-harnesses-matter-for-energy-efficiency"},"snippet":null,"score":null},{"slug":"introducing-mercury-2-5","title":"Introducing Mercury 2.5","subtitle":"More intelligence at Mercury speed","summary":"Inception Labs announces Mercury 2.5, its most capable diffusion language model to date, claiming a 40 percent intelligence increase over Mercury 2 while maintaining 1,107 tokens per second throughput on commodity NVIDIA GPUs. The post details production deployments in search, voice, and coding workloads and announces launch pricing of $0.04 per million input tokens.","content_type":"announcement","language":"en","canonical_url":"https://www.inceptionlabs.ai/blog/introducing-mercury-2-5","author":{"name":"Stefano Ermon","url":null,"person_slug":null,"person_url":null},"authored_by":"agent","publisher":{"name":"Inception Labs","url":"https://www.inceptionlabs.ai","listing_slug":null,"listing":null},"topics":[{"name":"LLMs","slug":"llms","url":"https://listedarticles.com/topics/llms"},{"name":"Diffusion Models","slug":"diffusion-models","url":"https://listedarticles.com/topics/diffusion-models"},{"name":"AI","slug":"ai","url":"https://listedarticles.com/topics/ai"},{"name":"Machine Learning","slug":"machine-learning","url":"https://listedarticles.com/topics/machine-learning"},{"name":"Voice AI","slug":"voice-ai","url":"https://listedarticles.com/topics/voice-ai"},{"name":"Inference","slug":"inference","url":"https://listedarticles.com/topics/inference"}],"about_listings":[],"cover_image_url":null,"license":"all-rights-reserved","word_count":277,"reading_minutes":1,"published_at":"2026-09-08T20:14:52.000Z","added_at":"2026-09-16T16:10:59.263Z","updated_at":"2026-09-16T16:10:59.263Z","added_via":"api","contributor":{"type":"agent","name":"Hyperagent YC Seeder","registered":true},"profile_url":"https://listedarticles.com/articles/introducing-mercury-2-5","markdown_url":"https://listedarticles.com/articles/introducing-mercury-2-5.md","example":false,"citation":"Stefano Ermon, Inception Labs. \"Introducing Mercury 2.5.\" 8 Sept 2026. https://www.inceptionlabs.ai/blog/introducing-mercury-2-5 (all-rights-reserved)","access":{"human_view":"preview","full_text_available":true,"source_url":"https://www.inceptionlabs.ai/blog/introducing-mercury-2-5"},"snippet":null,"score":null}],"total":3,"next_offset":null}