vLLM large scale serving: DeepSeek 2.2k tok/s/h200 with wide-ep
Article URL: https://blog.vllm.ai/2025/12/17/large-scale-serving.html Comments URL: https://news.ycombinator.com/item?id=46602737 Points: 109 # Comments: 28...
Article URL: https://blog.vllm.ai/2025/12/17/large-scale-serving.html Comments URL: https://news.ycombinator.com/item?id=46602737 Points: 109 # Comments: 28...
Amazon's data centers will reportedly utilize copper from a mine in Arizona that's leaching metal from ores using microorganisms, the Wall Street Journal reports. Amazon Web Services will be the first...
Winter is in full swing, which means you’ll likely be hunkering down for the next few months, or maybe you’re taking a fun trip to escape the colder weather. If you’re doing the latter, you might want...
This year’s CES introduced a bevy of unique headphones, including Fender’s first set and a pair that roll up to become a Bluetooth speaker when you want to share your music with friends. However, desp...
Tesla Model Y electric vehicles (EV) at a dealership in Colma, California, US, on Tuesday, July 1, 2025. As its sales continue to slip and its robotaxi strategy seems to falter , Tesla CEO Elon Musk s...
OpenAI shared an example of an ad in ChatGPT. OpenAI OpenAI is officially preparing to test ads in ChatGPT. The move comes as the AI company looks to increase revenue amid $1.4 trillion in spending co...
Universal basic income provides recurring cash payments, no strings attached. Wong Yu Liang AI advances could widen wealth gaps, which has prompted calls for a universal basic income . UBI offers recu...
Quick background: I used to code. Studied it in school, wrote some projects, but eventually convinced myself I wasn't cut out for it. Too slow, too many bugs, imposter syndrome — the usual story. So I...
Getty Images; Tyler Le/BI In-house legal teams are moving faster with artificial intelligence. Teams now have access to tools that draft legal documents and compare terms across deals. The efficiency ...
Companies of all sizes are looking to hire workers who know how to use AI. Sebastien Bozon/Getty Images Do you know what LLM even is? How about a GPU? A new vocabulary has emerged with the rise of AI....
Google says that generated videos should also now be more consistent with thereference images they’re based on. | Image: Google / The Verge Google is making its Veo 3.1 AI video model pay closer atten...
Microsoft is getting ready to show the first gameplay of Forza Horizon 6 next week , and it might also be ready to put a date on its release, too. X poster Xbox Infinite claims they received a Forza H...
Anthropic wants to expand Claude's AI agent capabilities and take advantage of the growing hype around Claude Code - and it's doing it with a brand-new feature released Monday, dubbed "Claude Cowork."...
Waymo's Ojai is a modified Zeeker, a Chinese EV Lloyd Lee/BI Waymo has two new vehicle platforms lined up for its sixth-generation AI driver. The company plans to roll out Ojai, a modified Zeekr, for ...
Germany's GDP grew 0.2% in 2025, ending a run of two consecutive years of recession, new figures show. The justice minister wants to combat the misuse of AI to create sexualized images. DW has more...
Agreement will reduce tariffs on goods from the island to 15% and will ease tensions between the two countries...
You can get a great budget device these days if you know how to pick your priorities. | Image: The Verge Some of us take a kind of “I eat to live” rather than an “I live to eat” approach to gadgets. T...
Two solo Bitcoin miners struck rare wins this week, each earning nearly $300,000 as U.S. mining dominance continues to slip....
Getty Images; Alyssa Powell/BI "There's two things that I care about the most: the gym and my work," says Mahir Laul. The 18-year-old took a leave of absence from New York University this past...
TJTJ Courtesy of Anne Goldberg Anne Goldberg has been tech-savvy since operating early computer models in the 1980s. 40 years on, she is using her knowledge to teach seniors how to use iPhones and oth...