Keep on to blur preview images; turn off to show them clearly
We explored GMI Cloud Inference Engine 2.0 @gmi_cloud - a unified API for running text, image, video, and audio models. No setup headaches. Just clean scaling and smooth outputs powered by NVIDIA DGX Cloud Lepton and GMI’s Cluster Engine. Here’s what we tested 👇
Performance improvements were easy to notice: • 1.46× faster inference • 25–49% higher throughput • 71% cheaper than the average V3 provider The new console UI makes deployment simple. We didn’t touch infra once. Everything runs through one API with elastic scaling built in.
卧槽，出大事了👀
我是河南人，不是中国人@yongchuTaffyOwO
é não foi dessa vez guys provavelmente o estagiário não repassou a nota vai ter que ser pelo caminho mais difícil mesmo 256/65536 já tá garantido
Kind / Bend / HVM / INets / λCalculus
RT @RuxandraTeslo: You have heard of AI slop in the context of short video creation. But the same principle applies when it comes to improv…
Author. Coder. CTO. θηριομάχης. Building: https://t.co/otXT4Wy6WR. Writing: https://t.co/dBPBtyCIHw.
RT @kennyholtz: Good idea! Reminds me of Buffett's simple fix: "I could end the deficit in 5 min. Pass a law that says that anytime there…
GP @a16z — Building American Dynamism 🇺🇸 — Anthropologist — Formerly Founder/CEO @OpenDNS — Lokah Samastah Sukhino Bhavantu
RT @zhang_benita: If you are interested in Kimi K2 thinking, you can check out this interview with Yang Zhilin, founder of Kimi (with Chine…
🇦🇺 Co-founder: @AnswerDotAI & @FastDotAI ; Prev: professor @ UQ; Stanford fellow; @kaggle president; @fastmail/@enlitic/etc founder https://t.co/16UBFTX7mo