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
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
3,543
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
12,789
nikki and momoten project logo github.com/nihui/nikki github.com/nihui/momoten
1
16
2,274
momoten: Vulkan compute on top of OpenCL Bring Vulkan compute to older GPUs Bypass missing, outdated, or buggy Vulkan drivers Potentially faster than native Vulkan Run ncnn Vulkan workloads without shader changes github.com/nihui/momoten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
2,239
spacemit k3 pico itx
7
76
4,571
Replying to @izutorishima
tested on amd rx9060xt 😇
1
2
445
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…
🤖 Made with AI
3
31
2
299
42,211
qwenimage-ncnn-vulkan added support for Qwen-Image-2.1 4-step LoRA and ControlNet It runs faster than pytorch-rocm or sd.cpp on my RX9060XT machine Hope my tool proves helpful to you :) github.com/nihui/qwenimage-n…
2
8
1
61
4,468
洗衣机里有 LVGL
9
64
6,206
YuzukiNeko
10
12
1
291
8,321
一眼就能区分出AI的提交
76
17
3
740
90,480
nvidia专家在 SIGGRAPH 2026 分享vulkan机器学习应用和进展 有6页PPT带着ncnn项目~ ​特别举例了ncnn极小的二进制分发,超分和插帧的应用 youtu.be/savTuEPWhwA?si=bJhl…
53
2
57
7,930
一天去了两个地方的必胜客,把两套联名套餐玩具全买到了~
6
2,183
无限暖暖必胜客主题店打卡
6
52
4,339
github.com/TencentYoutuResea… mollm is a small C++ LLM runtime for ARM CPUs, with experimental Apple Metal support
1
2
1
24
4,615
修复了 bf16 精度不足引起的瑕疵
hunyuan3d-ncnn project preview The model's surface still has flaws and needs improvement ./hunyuan3d-ncnn-vulkan -i in.png -o textured.glb --texture
1
47
6,847