编译版本，默认配置，android-ndk-r28c，xcode 15.2，ubuntu-22.04，ubuntu-24.04，vs2015，vs2017，vs2019，vs2022，emscripten-3.1.28
| file | content | arch |
|---|---|---|
| ncnn-full-source.zip | 包含全部 submodule 代码的完整源码 | |
| ncnn-android.zip | android 静态库/动态库 | armeabi-v7a + arm64-v8a + x86 + x86_64 + riscv64 |
| ncnn-android-vulkan.zip | android 静态库/动态库，支持 GPU | armeabi-v7a + arm64-v8a + x86 + x86_64 + riscv64 |
| ncnn-apple.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst + watchos + watchos-simulator + tvos + tvos-simulator + visionos + visionos-simulator | arm64 + arm64e + x86_64 |
| ncnn-apple-vulkan.zip | apple xcframework，ios + ios-simulator + macos + mac-catalyst + watchos + watchos-simulator + tvos + tvos-simulator + visionos + visionos-simulator，支持 GPU | arm64 + arm64e + x86_64 |
| ncnn-ios.zip | ios 静态库 | arm64 |
| ncnn-ios-vulkan.zip | ios 静态库，支持 GPU | arm64 |
| ncnn-ios-simulator.zip | ios simulator 静态库 | x86_64 + arm64 |
| ncnn-ios-simulator-vulkan.zip | ios simulator 静态库，支持 GPU | x86_64 + arm64 |
| ncnn-macos.zip | macos 静态库 | x86_64 + arm64 |
| ncnn-macos-vulkan.zip | macos 静态库，支持 GPU | x86_64 + arm64 |
| ncnn-mac-catalyst.zip | mac catalyst 静态库 | x86_64 + arm64 |
| ncnn-mac-catalyst-vulkan.zip | mac catalyst 静态库，支持 GPU | x86_64 + arm64 |
| ncnn-watchos.zip | watchos 静态库 | armv7k + arm64_32 |
| ncnn-watchos-simulator.zip | watchos simulator 静态库 | x86_64 + arm64 |
| ncnn-tvos.zip | tvos 静态库 | x86_64 + arm64 |
| ncnn-tvos-vulkan.zip | tvos 静态库，支持 GPU | x86_64 + arm64 |
| ncnn-tvos-simulator.zip | tvos simulator 静态库 | x86_64 + arm64 |
| ncnn-tvos-simulator-vulkan.zip | tvos simulator 静态库，支持 GPU | x86_64 + arm64 |
| ncnn-visionos.zip | visionos 静态库 | arm64 |
| ncnn-visionos-vulkan.zip | visionos 静态库，支持 GPU | arm64 |
| ncnn-visionos-simulator.zip | visionos simulator 静态库 | x86_64 + arm64 |
| ncnn-visionos-simulator-vulkan.zip | visionos simulator 静态库，支持 GPU | x86_64 + arm64 |
| ncnn-ubuntu.zip | ubuntu linux 静态库/动态库，支持 GPU，模型转换工具 | x86_64 |
| ncnn-windows.zip | windows 静态库/动态库，支持 GPU，模型转换工具 | x86 + x64 + arm + arm64 |
| ncnn-webassembly.zip | webassembly 静态库 | wasm32 + simd + threads + simd-threads |
新增flip算子和pnnx torch.flip的转换
clip x86 avx512循环剩余优化
tanh和unaryop x86 avx512循环剩余优化(@lfalive)
sigmoid x86 avx512循环剩余优化(@futz12)
instancenorm x86优化(@futz12)
groupnorm x86 sse2/avx/avx512优化
groupnorm arm neon优化(@mmyyy22)
sigmoid和部分数学函数 loongarch lsx/lasx 优化(@AtomAlpaca)
shufflechannel riscv rvv/zfh/zvfh/xtheadvector优化(@AtomAlpaca)
layernorm riscv rvv/zfh/zvfh/xtheadvector优化(@Deepdive543443)
layernorm vulkan优化(@futz12)
使用size_t类型改善超大尺寸tensor的支持
修复x86 convolution int8 在启用avx512vnni时崩溃
修复android asset datareader在新android系统和部分手机上崩溃的问题
初始化layer featmask为空
简化layernorm naive c实现
修复convdw int8 dequantize pack8
使用putenv和平台相关api修复llvm-mingw编译问题(@zhuzeitou)
使用combine_x用于sse/avx vector拼接
修复rnn/lstm/gru int8测试因rounding导致的差异
更新ruapu探测risc-v zfh zvfh xtheadvector和动态分发
删除已废弃的 Extractor::set_num_threads/set_vulkan_compute api
修复cmake时编译器支持avxvnniint16的探测
修复windows nt内核不存在GetLogicalProcessorInformationEx时的崩溃问题(@futz12)
cmake find_package(ncnn)支持指定最低版本并输出ncnn版本号(@Willaaaaaaa)
benchncnn跑GPU时跳过int8模型(@c8s-wk)
支持Windows XP目标平台编译和新增msvc/mingw/clang的windows-xp ci(@AtomAlpaca @Sugar-Baby)
修正ppocr中ctc decode后处理规则(@futz12)
改善benchncnn中printf对size_t类型格式化参数兼容(@whyb)
更新glslang
最大支持gpu数量到32(@tpoisonooo)
支持nvidia headless vulkan
检测vulkan扩展 VK_KHR_shader_integer_dot_product VK_KHR_shader_bfloat16 VK_KHR_shader_float_controls2 VK_NV_cooperative_vector VK_NV_cooperative_matrix2 VK_EXT_shader_float8 VK_KHR_vulkan_memory_model
支持任意 cooperative matrix MNK size查询
修复vulkan-sdk支持VK_KHR_acceleration_structure时的编译错误
1d/2d Mat和VkMat总是会分配对齐的size，调整cstep策略
删除全部layer中vkimagemat类型输入输出的forward实现
删除layer support_image_storage和option use_image_storage字段
删除全部layer中pack8 shader实现
支持无graphics queue的vulkan驱动
vulkan fp16 packed在pack1时也使用半精度存储
跳过vulkan 1d权重上传前的cpu-pack
修复当cpu支持avx512时vulkan上传pack16数据的错误
修复有关localsize非subgroupsize倍数的vulkan validation error
总是将localsize设为subgroupsize的整数倍
合并khr/nv双版本cooperative matrix shader
vulkan convolution 1x1s1d1支持任意mnk size和统一elempack
vulkan convolution gemm支持任意mnk size和统一elempack
vulkan convolution winograd支持任意mnk size和统一elempack
vulkan deconvolution gemm支持任意mnk size和统一elempack
vulkan gemm支持任意mnk size
vulkan absval 统一elempack shader
vulkan sigmoid和激活函数统一elempack shader(@futz12)
vulkan unaryop 统一elempack shader(@weikangqi)
支持vulkan int8 packing/quantize/dequantize/requantize
检测vulkan扩展 VK_EXT_robustness2 VK_KHR_robustness2 调整ssbo对齐尺寸，修复nvidia新驱动中waitfence -4问题(@Upliner)
pnnx增强huggingface/transformers的attention/sdpa变种转换，有 albert bart bert blenderbot camembert chinese clip ctrl deberta distilbert electra flaubert fsmt funnel gpt2 layoutlm longformer lxmert marian mbart mobilebert mt5 openai pegasus prophetnet reformer roberta squeezebert t5 xlm xlnet
pnnx增强ppocrv5 onnx转换
pnnx支持转换onnx MaxPool auto_pad same
pnnx支持转换torch.reshape_as
pnnx新增logical_and/not/or/xor测试
pnnx总是为test_inference()生成有效的静态shape
pnnx自动处理conv/convtranspose/linear中的weight norm转换
pnnx匹配更多pad-conv模式
pnnx支持onnx flatten无axis参数的转换
pnnx修复onnx groupnorm转换
pnnx修正生成python脚本时inputshape越界崩溃问题
pnnx转ncnn时处理batch index相关的squeeze/unsqueeze
pnnx转ncnn不再删除模型末尾的reshape/permute
pnnx在windows上设置codepage utf8解决乱码问题
支持OMP_THREAD_LIMIT环境变量约束pnnx转换onnx模型的线程数
pnnx更新torch-2.8
FAQ新增ncnn deepwiki链接(@tpoisonooo)
更新readme有关cpu/gpu兼容性的表格
更新中文glsl扩展文档(@chri321)
更新glsl文档中去除废弃的image function(@GIBEREZ)
修正esp32编译文档中的命令错误(@Willaaaaaaa)
使用spdx风格的文件头协议
新增yolo11示例
新增yoloworld示例
新增ppocrv5示例
新增piper-tts示例
禁用pypi free threading wheel编译
迁移gpu swiftshader/lavapipe ci到ubuntu25
在self-hosted runner上使用预置的codecov二进制程序
ci更新riscv spacemit工具链和qemu
ci更新riscv xuantie工具链和qemu
迁移msvc ci到windows-2022并运行时安装vs2015/vs2017(@bil0077)
vs2015/vs2017 ci使用旧版本windows sdk修复编译
ci修复linux riscv64依赖缺失错误(@Jzow)
新增AK3918(AK)和SS928(hisi)的cmake交叉编译配置(@chentyjpm)
ci新增linux riscv32和c907交叉编译配置(@YuzukiTsuru)
新增MUSE Pi Pro Spacemit M1性能数据(@ChinaYingXi)
New Contributors
- @ChinaYingXi made their first contribution in #6074
- @lfalive made their first contribution in #6096
- @zhuzeitou made their first contribution in #6101
- @mmyyy22 made their first contribution in #4080
- @Jzow made their first contribution in #6133
- @chri321 made their first contribution in #6162
- @Willaaaaaaa made their first contribution in #6165
- @c8s-wk made their first contribution in #6174
- @weikangqi made their first contribution in #6179
- @Copilot made their first contribution in #6204
- @bil0077 made their first contribution in #6210
Full Changelog: 2025050...2025091