Built: avante.nvim Building: https://xitter.cf/t.co/kQss3piJs8 https://xitter.cf/t.co/pfq9srNgsd https://xitter.cf/t.co/QhQRLD4zQo https://xitter.cf/t.co/6ERz2HMx0f https://xitter.cf/t.co/fpGnPR5t9C https://xitter.cf/t.co/cBN1yzJPIG
无
Joined May 2010
- Tweets21.3K
- Following4.6K
- Followers98.2K
- Likes19.9K
yetone retweeted
Introducing Kimi K3.1 Pro: our most capable 3T-class open-weight model.
🔹 1M-token context, 2.8T total / 104B active params (MoE), Multimodal.
🔹 Full-project coding: games in Unreal, Unity & Godot.
🔹 Excels at parametric 3D modeling in Blender & CAD.
🔹 More reliable at finance work: Accurate modeling with hallucination down by 65%.
🔹 Matching the strongest proprietary models across coding, agentic and knowledge benchmarks.
Kimi K3.1 Pro and K3.1 Pro Highspeed (2–3× faster) are now live on Kimi.ai, Kimi Work, Kimi Code, and the Kimi API.
Open weights by Nov 4, 2026.
🔗 API: platform.kimi.ai
🔗 Tech blog: kimi.ai/blog/kimi-k3-1-pro
帮转，Design Engineer 永远是时代的神。
大家好，我正在寻找远程的 Design Engineer 机会。
过去几年作为合伙人共同运营 Zolplay，重心在产品设计与交互体验。经历过早期初创团队，也负责过上市公司项目组，主导过多款产品从 0 到上线交付。
个人介绍与作品集：cuvii.dev/work
欢迎交流或推荐，感激。
牛啊！
DeepSeek just open sourced its high-performance, large-scale inference framework DeepInfer in Apache-2.0 license.
github.com/deepseek-ai/DeepI…
Supported features:
- Optimized kernels, model and sampler runtime
- Parallelism: Attention DP / balanced CP, MoE EP + EPLB
- DSpark and confidence-scheduled verification
- SWA bounded replay
- Asynchronous scheduling (zero-overhead batch scheduler)
- Batch-invariant inference
- Deterministic sampling
- Structured output
我只想说 ip.skk.moe 是我的必备网站，背的比我自己的手机号还熟。
烧了点 Opus 5.5 写了一个测速网站。
speed.skk.moe
（欢迎大家一起来寻找神秘小彩蛋）
我在推上还是比较喜欢骂骂那些阴湿的人，以及话痨一下自己的想法。所以正在渐渐的把 Magpie 的反馈渠道收拢到 Discord 里，希望大家去 Magpie Discord server 里去进行反馈，那边会及时的响应的，谢谢大家。
discord.gg/vGSnD3ZKQF
