If anyone else is running this on an RTX 5090, https://github.com/Neroued/ninfer as inference engine gets me ~138 tokens/second, roughly double what I get with a naive llama.cpp setup.
We do. The Cerebras line of Wafer Scale Engines is exactly an entire wafer of cores running in parallel with fast memory next to each one. It's intended for very high throughput LLM inference.…
It's also incorrect. They could just use youtube-nocookie.com instead if tracking cookies are disabled. https://support.google.com/youtube/answer/171780?hl=en#zippy...
That becomes a problem when Google Chrome limits the number of filter rules extensions can add. https://developer.chrome.com/docs/extensions/develop/concept...
A good reminder to read about how it almost didn't turn out alright. * https://time.com/10228/obamas-trauma-team/ * https://www.pauladamsmith.com/blog/2023/10/the-10-year-anniv... (And of course the related Hacker News…
Templafy | Copenhagen, Denmark; New York City, NY | Hybrid (2-3 days onsite) | Full-time | Visa sponsorship | https://www.templafy.com/ Short pitch: Web app and Office add-ins for template management, document…
Templafy | Copenhagen, Denmark; Berlin, Germany; New York City, NY | Hybrid (2-3 days onsite) | Full-time | Visa sponsorship | https://www.templafy.com/ Short pitch: Web app and Office add-ins for template management,…
If anyone else is running this on an RTX 5090, https://github.com/Neroued/ninfer as inference engine gets me ~138 tokens/second, roughly double what I get with a naive llama.cpp setup.
We do. The Cerebras line of Wafer Scale Engines is exactly an entire wafer of cores running in parallel with fast memory next to each one. It's intended for very high throughput LLM inference.…
It's also incorrect. They could just use youtube-nocookie.com instead if tracking cookies are disabled. https://support.google.com/youtube/answer/171780?hl=en#zippy...
That becomes a problem when Google Chrome limits the number of filter rules extensions can add. https://developer.chrome.com/docs/extensions/develop/concept...
A good reminder to read about how it almost didn't turn out alright. * https://time.com/10228/obamas-trauma-team/ * https://www.pauladamsmith.com/blog/2023/10/the-10-year-anniv... (And of course the related Hacker News…
Templafy | Copenhagen, Denmark; New York City, NY | Hybrid (2-3 days onsite) | Full-time | Visa sponsorship | https://www.templafy.com/ Short pitch: Web app and Office add-ins for template management, document…
Templafy | Copenhagen, Denmark; Berlin, Germany; New York City, NY | Hybrid (2-3 days onsite) | Full-time | Visa sponsorship | https://www.templafy.com/ Short pitch: Web app and Office add-ins for template management,…
Templafy | Copenhagen, Denmark; Berlin, Germany; New York City, NY | Hybrid (2-3 days onsite) | Full-time | Visa sponsorship | https://www.templafy.com/ Short pitch: Web app and Office add-ins for template management,…