Pinned Tweet
ncnn telegram chat group 技术交流电报组
ncnn community
t.me/ncnnyes
opencv-mobile updated 5.1.0 ➡️ github.com/nihui/opencv-mobi…
mesa-turnip-android-driver updated 26.3.0➡️github.com/nihui/mesa-turnip…
The download count for the mesa-turnip-android-driver is unusually high; I don’t really understand why. 🧐
1
12
2,465
三个月后...它从 13 t/s -> 128 t/s
它进化了,我也成长了😋
折腾到大半夜的,汇报下这几天深耕 ncnn-MoE-Runtime 的进展!
好消息是,它可以在 5070ti (16G vRAM)+ 9800X3D + 32G (7600Mhz) 内存组合下情况下,可以跑起 GPT-OSS-120B 的模型
且最高峰值可达 13.36 token/s
想到将来能够通过更低的硬件成本,能够运行起更多的 LLM 时就非常的兴奋!
接下来继续优化,让我来探索下极限边界在哪!
项目地址:github.com/crafcat7/ncnn-MoE…
蹲点大佬们的 star(目前优化还没上传!目前仓库内仅能运行起 120b 模型)
nihui retweeted
This screenshot shows Qwen3-0.6B LLM running on a pure IA32 processor such as the Intel Core Solo T1350, based on github.com/crafcat7/ncnn-MoE… from @crafcat7.
I reverse engineered ARKit to learn how it works and bust the myths.
It is a ML model that takes a 128x128 pixel RGB selfie and spits out the blend shapes, plus post-processing.
I made it work on macOS, with any webcam. OpenVT mac builds coming soon.
gist.github.com/hoshinolina/…
libwaifu/waifu2d 第一版完成!🎉
虽然头发和口型还有些问题,但至少waifu能动了!目前整套流程都是自动化的:AI 生成图片→See-through模型分层→驱动动画,无需任何手工修改。感谢See-through项目:github.com/shitagaki-lab/see…
如果感兴趣,欢迎给 libwaifu 点个 ⭐
github.com/ling0322/libwaifu
nikki and momoten project logo
github.com/nihui/nikki
github.com/nihui/momoten
1
16
2,272
momoten: Vulkan compute on top of OpenCL
Bring Vulkan compute to older GPUs
Bypass missing, outdated, or buggy Vulkan drivers
Potentially faster than native Vulkan
Run ncnn Vulkan workloads without shader changes
github.com/nihui/momoten
zhuanlan.zhihu.com/p/2096952…
🤖 Made with AI
Vulkan 1.4.366 已经收录 nikki 和 momoten 的 driver ID
VK_DRIVER_ID_NIKKI = 33
VK_DRIVER_ID_MOMOTEN = 34
nikki 和 momoten 两个驱动 id 已经正式合并到 vulkan-docs
github.com/KhronosGroup/Vulk…
1
16
2,493
nikki 和 momoten 两个驱动 id 已经正式合并到 vulkan-docs
github.com/KhronosGroup/Vulk…
qwenimage-ncnn-vulkan 已支持 qwen-image-2.1-turbo
8步出图
github.com/nihui/qwenimage-n…
预告:4G内存 + 2G显存 跑BF16精度 qwen-image-2.1 1024x1024 出图并且速度不变慢
用 ncnn 跑 Qwen-Image-2.1:完整 BF16、2GB 显存和全平台 Vulkan
zhuanlan.zhihu.com/p/2088230…
github.com/nihui/qwenimage-n…





















