跳到正文
Hacker News:AI 熱帖·· 4 天前AI 評分47

Cerebras 解耦推理

Cerebras Disaggregated Inference

AI 導讀

Cerebras 解耦推理成為 Hacker News 討論焦點,有留言稱其吞吐量較 b4 高 5 倍,與標準方案相比每秒 token 數相同,達 10 倍。討論亦涉及 CS-3 晶圓的温度、閒置耗電及使用年限;一名自稱任職 Cerebras 的留言者稱,CS-3 平均運作温度低於 65c,並反駁「Ghost tokens」會令壽命縮短 3 倍的説法。

正文

Image 1Hacker Newsnew | past | comments | ask | show | jobs | submitlogin

Cerebras Disaggregated Inference (cerebras.ai) 22 points by emschwartz1 hour ago | hide | past | favorite | 5 comments help Image 2aabdi33 minutes ago | next[–] 5x throughput more than b4, same 10x tokens/s as compared to standard. looks like disagg/wide ep is applicable to cerebras chips as well. kind of amazing. https://www.cerebras.ai/blog/how-we-deploy-trillion-paramete... reply Image 3augment_me40 minutes ago | prev[–] Have they solved the issue yet where they need to keep running ghost tokens to keep the board hot to prevent it from cracking, which causes massive energy draw in idle, and reduces lifetime by 3 times the estimate? https://culperresearch.com/wp-content/uploads/2026/10/Culper... reply Image 4eh826 minutes ago | parent[–] The short seller report contains a bunch of errors: 1. The CS-3 operates on average at <65c, well below its thermal limits. Considering the actual thermal parameters of the wafer, using the short seller's own temperature equation would imply the wafer can operate at 85c for 33 years 2. "Ghost tokens" are not unique to Cerebras and the 3x lifespan reduction claim is based on extrapolating GPU figures which is a big logical leap 3. "since the introduction of the CS-3 in 2024, less than half of one percent of all CS-3 wafers deployed have been decommissioned." https://cerebras.ai/blog/what-it-took-to-build-wafer-scale-a... Disclaimer: I work at Cerebras reply Image 5augment_me10 minutes ago | root | parent | next[–] Very interesting! Thanks for answering with your take, and the link. Questions: 1) What is the idle power draw of the chip? Is the 80% number wrong? Nvidia is idling at around 180W/15% of their max for B300. So saying that "it's not unique to Cerebras" is meaningless if we don't consider the power draw itself 2) Decommissioned is not the same as RMA:d/refurbished/redeployed, so giving this number is kind of dodging the question IMO reply Image 6lukeify6 minutes ago | root | parent | prev[–] So which Cerebras statement is in error then? > First, in Cerebras’s preliminary IPO prospectuses filed through December 2025, the Company assigned its computer equipment useful lives of just 1.5 to 3 years – in-line with both our Arrhenius modeling and what many of the Company’s hardware customers have described to us.4 Just four months later, in the Company’s April 2026 S-1, Cerebras nearly doubled that range to 3 to 5 years – a change that significantly inflated reported margins. The Company appears to have never explained the reason for this change. Was the useful life of a wafer 1.5–3 years on your IPO filing or 3–5 years in your S-1? Hard to believe a company with such skilled engineers couldn't figure out the correct useful wafer life given existing industry data. Or (more likely) are we just looking at standard corporate BS? reply Image 7 Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact Search:

來源:Hacker News:AI 熱帖 · news.ycombinator.com