Kimi K3.1 Pro's full model weights are now available.
This is a dev post classified by AGK Intelligence as Hosting & infra (a launch), kept by the Dev Radar because it carries real work, not commentary.
Kimi K3.1 Pro's full model weights are now available. Huawei Ascend delivered Day-0 inference support through both vLLM-Ascend and SGLang. The adaptation enables Kimi K3.1 Pro inference deployment across: • Ascend Atlas 800 A3 • Atlas 900 A3 SuperPoD • Ascend 950 SuperPoD series You can now deploy Kimi K3.1 Pro on Huawei's Ascend hardware using either inference framework.
Posted by 智东西China AI News (3k followers) 3 h ago · 1 likes · 225 views · view the original post on X. Kept by the Dev Radar as Hosting & infra.
More dev work like this
- Catching glowing starlight from the twilight sky and filling the basket with sweet… — @alibaba_cloud
- 🚀Kimi just launched Kimi Hosted Agents — @Chinazhidx
- Max 68% off your first Token Plan — the easiest way to try the latest models in one place. — @alibaba_cloud
- Kimi K3.1 Pro is now live on Alibaba Cloud Model Studio & Qwen Cloud! — @alibaba_cloud
- Introduction to Docker by Bobby Iliev (2024) is now in @ChapterPal's collection of open… — @burkov
- Building a trusted AI cloud starts with openness, security and efficiency. Felix Liu,… — @alibaba_cloud
- Coming soon, more ways to run Deepseek sub 128GB Ram on MLX-Serve. — @ddalcu
- Phaze CEO @boxerbk explains why AI agents shouldn't have to take over your computer to… — @MTSlive
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. 31.7k posts from 5k X accounts over the last 21 days, 9.3k tools, 12 markets. New posts are collected several times an hour and the full ranking is recomputed every hour — last update 2026-11-05 06:57 UTC. Full method.