nihui (@nihui) header
nihui (@nihui) profile picture

春雨为观,香月为邻 | 喜欢玩游戏时看风景 | 想成为优秀的程序员 | 看上去是女装大佬实际并不是( | 上海老阿姨 | qwqwqwq

Shanghai
Joined July 2008
Photo by nihui (@nihui)Photo by nihui (@nihui)Photo by nihui (@nihui)Photo by nihui (@nihui)Photo by nihui (@nihui)Photo by nihui (@nihui)Photo by nihui (@nihui)Photo by nihui (@nihui)Photo by nihui (@nihui)Photo by nihui (@nihui)
ncnn telegram chat group 技术交流电报组 ncnn community t.me/ncnnyes
10
4
1
171
h3image-ncnn 初版跑通,优化中... 还是4g内存起步吧
打算先出 h3image-ncnn-vulkan bf16全精度,2g内存+2g显存可用
4
5
61
3,540
打算先出 h3image-ncnn-vulkan bf16全精度,2g内存+2g显存可用
10
1
2
75
8,520
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
nihui retweeted
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)
1
7
1,056
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.
2
2
1
7
941
古法AI编程 ctrl c 复制 gpt review comment ctrl v 贴给 claude 不给AI相互调用,要是吵架起来,token 灰飞烟灭
17
1
75
5,462
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/…
6
37
4
301
8,641
群友抢先内测中🥹
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
6
4
122
12,787
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
21
113
4
1,574
52,113
GPT得来终觉浅,绝知此事要躬行
1
71
4,142
nikki and momoten project logo github.com/nihui/nikki github.com/nihui/momoten
1
16
2,272
为什么 telegram private channel 还会天天几十条bot垃圾信息?
6
15
4,130
codex for oss 6个月白嫖到期了 新的申请又迟迟没有好消息 只能买淘宝代充了 quq
4
32
4,278
momoten: Vulkan compute on top of OpenCL Bring Vulkan compute to older GPUs Bypass missing, outdated, or buggy Vulkan drivers Potentially faster than native Vulkan Run ncnn Vulkan workloads without shader changes github.com/nihui/momoten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
1
2
1
18
2,237
Vulkan 1.4.366 已经收录 nikki 和 momoten 的 driver ID VK_DRIVER_ID_NIKKI = 33 VK_DRIVER_ID_MOMOTEN = 34
1
16
2,493
授人鱼不如授人以渔 皆不如授ai以token
4
1
32
3,958
spacemit k3 pico itx
7
76
4,569
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…
12
32
4
300
38,732