Realtime and accumulated experts stats… coming to CuteAFD v5
This is a AI post classified by AGK Intelligence as AI infra & evals (a launch), kept by the AI Radar because it carries real work, not commentary.
Realtime and accumulated experts stats… coming to CuteAFD v5 Now all the families of models have expert route counters integrated and you can query via API or stream it live on a new dashboard page. I dont think we’ll ever go down the expert paging path since I’d rather buy more sparks than 1TB of slow RAM for my Server … but still I think this is useful and interesting to be able to see. Maybe if you hack your own version of cute for paging it could be useful to you. Thanks to @O_Drater for the initial impl. Below find Mistral Large 4 real routes image for a prefill check
Posted by tj ☄️ (3.1k followers) 13 h ago · 3 likes · 135 views · view the original post on X. Kept by the AI Radar as AI infra & evals.
More AI work like this
- The enterprise AI bottleneck has moved from models and GPUs to the data path. — @Dell
- AMD Localmaxxers are getting serious about inferencing. 🤯 — @TeksEdge
- We evaluated Nexus on 7 benchmarks and 1,222 tasks. It defines the Pareto frontier. — @FireworksAI_HQ
- There is a 560B model running with its full 1M context on 2x DGX Sparks by @andersjw_. — @plotarmordev
- 免费GPT的API，手快有手慢无 — @mylifcc
- TensorFold 1.2.4 is out. 🚀 — @ashxhart
- AWS is making it easier to run several smaller models on the same GPU. — @markfenner
- The @nvidia Jetson Orin Nano is back in the lab. — @jmurillocode
Every post is read and classified by AGK Intelligence: what it is, which market it belongs to, and whether the link is a real tool. 65.2k posts from 5k X accounts over the last 14 days, 10.5k tools, 19 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-07 16:40 UTC. Full method.