@nihui

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
github.com/nihui
Joined July 2008
  • Tweets6.2K
  • Following936
  • Followers44.2K
1.2KMedia
ncnn telegram chat group 技术交流电报组 ncnn community t.me/ncnnyes

ncnn community

make neural network faster :D

t.me
10
4
1
171
GPT得来终觉浅，绝知此事要躬行
1
51
2,253
nikki and momoten project logo github.com/nihui/nikki github.com/nihui/momoten
1
16
1,631
为什么 telegram private channel 还会天天几十条bot垃圾信息？
6
15
3,537
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
31
3,733
momoten: Vulkan compute on top of OpenCL Bring Vulkan compute to older GPUs Bypass missing, outdated, or buggy Vulkan drivers Potentially faster than native Vulkan Run ncnn Vulkan workloads without shader changes github.com/nihui/momoten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
1,753
Vulkan 1.4.366 已经收录 nikki 和 momoten 的 driver ID VK_DRIVER_ID_NIKKI = 33 VK_DRIVER_ID_MOMOTEN = 34
nihui@nihuiOct 22
nikki 和 momoten 两个驱动 id 已经正式合并到 vulkan-docs github.com/KhronosGroup/Vulk…

Register nikki and momoten driver IDs (#2840) · KhronosGroup/Vulkan-Docs@67e3092

github.com
1
16
2,156
授人鱼不如授人以渔 皆不如授ai以token
4
1
32
3,647
nikki 和 momoten 两个驱动 id 已经正式合并到 vulkan-docs github.com/KhronosGroup/Vulk…

Register nikki and momoten driver IDs (#2840) · KhronosGroup/Vulkan-Docs@67e3092

github.com
2
1
2
15
4,525
qwenimage-ncnn-vulkan 已支持 qwen-image-2.1-turbo 8步出图 github.com/nihui/qwenimage-n…

Release Release 20261010 · nihui/qwenimage-ncnn-vulkan

support qwen-image-2.1-turbo https://huggingface.co/nihui-szyl/qwen-image-ncnn/tree/main/qwenimage21-turbo

github.com
5
1
54
4,697
spacemit k3 pico itx
7
75
4,314
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
nihui@nihuiSep 29
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…
8
29
2
268
24,390
Qwen-Image-2.1 running on Intel B580! Thanks to @nihui for qwenimage-ncnn-vulkan
1
11
1,043
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
289
40,075
其实没有我你分不出那些差别 结局还能多明显 别说nihui难过 别说你想改变 AI的人不用道歉😐
11
90
7,211
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
4,369
nihui retweeted
Lei Zhang
@LeiLMxSep 26
Visualizing to learn model internals in the agentic era can be surprisingly low-friction. I had Codex one-shot architecture notes earlier for several recent OSS models—DeepSeek V4/V4.1, GLM 5.3, and Kimi K3—specifically from a kernel-development perspective: tensor contracts, exact shapes/layouts, attention variants, KV-cache representation, precision choices, dataflow, and operator boundaries. Sharing in case they’re useful to others: lei.chat/models/

Model Architectures | Lei.Chat()

Interactive, source-grounded maps of modern large-model architectures.

lei.chat
5
19
1
116
10,501
好耶，libwaifu支持Qwen-Image-2.1成功🎉 github.com/ling0322/libwaifu
1
1
24
2,558
文生图性能优化 10%~20% (cooperative matrix) 图编辑性能优化 40%~85% (prefix cache) 调整低显存的 tile 策略，KV cache host swap，进一步降低显存占用，防止多图输入的显存溢出 github.com/nihui/qwenimage-n…

Release Release 20260924 · nihui/qwenimage-ncnn-vulkan

optimize image editing efficiency massively with prefix cache optimize bf16 gemm cooperative matrix kernel efficiency optimize strategy for low_vram, vae tile size and KV cache cpu staging

github.com
8
3
70
6,853
预告：controlnet 和 lora safetensor 😋
1
1,287
洗衣机里有 LVGL
9
64
6,069
Load more