"On the four clear-cut outages, the [DiffusionGemma] model was confident on its first…

This is a dev post classified by Jev as Hosting & infra (a tutorial), kept by the Dev Radar because it carries real work, not commentary.

"On the four clear-cut outages, the [DiffusionGemma] model was confident on its first pass and returned in about 180 ms, hitting Jev’s sub-200ms target on a single serverless L4 GPU." https://medium.com/google-cloud/how-to-build-a-jev-style-classifier-with-diffusiongemma-and-vllm-ef2e0bfa9ad7 < good stuff from @kweinmeister

Posted by Richard Seroter (36.8k followers) 1 h ago · 2 likes · 160 views · view the original post on X. Kept by the Dev Radar as Hosting & infra. Tools mentioned: medium.com.

More dev work like this

• 👀 — @xeophon
• Connecting industrial devices shouldn’t mean rebuilding every application around each… — @DanKornas
• ClusterMAX 3.0 is here! — @JordanNanos
• Introducing Rollouts. — @cursor_ai
• SpAItial trains world models on Crusoe, over 97% scaling efficiency in benchmarks, with… — @CrusoeAI
• Want to run GLM 5.3 Flash EXL3 on 2x DGX Spark like I do? My full config is now in the… — @plotarmordev
• Run Ollama on GPU infrastructure you choose, with your model, runtime, and data under… — @CtrlIQ
• Self-hosted GitLab is now a supported source provider on Laravel Private Cloud. — @laravel

Every post is read and classified by Jev (TypeSafe): what it is, which market it belongs to, and whether the link is a real tool. 22.9k posts from 5k X accounts over the last 21 days, 2.7k tools, 12 markets. Collected every 5 minutes, fully re-ranked every hour — last update 2026-09-23 22:52 UTC. Full method.