android ios macos linux windows webassembly watchos tvos visionos 预编译库 20260113 e956fbf
编译版本,默认配置,android-ndk-r29,xcode 16.4,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sdpa layer和pnnx torch.scaled_dot_product_attention的转换,支持gqa合并 新增rotaryembed layer sdpa支持kvcache multiheadattention支持kvcache layer可选实现support_vulkan_packing layer可选实现support_vulkan_any_packing vulkan支持bf16开关,支持旧显卡模拟转换bf16 rmsnorm vulkan优化(@futz12) selu vulkan优化(@futz12) vulkan eltwise统一elempack shader 简化vulkan cast 改善M较小时在N上切块的多线程调度 gemm x86 avx512采用N维度16切块优化 sdpa x86使用gemm和softmax优化(@futz12) arm neon数学函数优先使用fma指令优化(@Abandon-ht) unaryop tan rvv优化(@ihb2032 @lyd1992) 新增cmake NCNN_WINXP开关,不再主动定义_WIN32_WINNT宏 c-api新增ncnn_version_number()接口返回数值 c-api新增更多option setter getter接口 net加载模型接口新增wchar_t参数类型 新增float8和bfloat8转换函数(@chloeee99) 格式化glsl文件 删除shader注释和额外的空格 不再编译onnx2ncnn benchncnn内置模型param,运行时不再需要param文件 修复modelwriter访问空bias数据崩溃问题(@csukuangfj) 修复param解析时尝试对已读取数据再次读取的逻辑错误(@futz12) 修复softmax多线程尾部余数的错误,优化倒数计算(@futz12) 修复msvc编译器x86 lstm int8开启vnni指令集时计算错误 修复x86 lstm int8越界读写问题 修复加载模型param出错时的退出逻辑(@Cat-myq) 修复vulkan驱动返回无效subgroup size导致加载卡死的问题(@Cat-myq) 修复加载模型时CRLF行尾解析逻辑错误(@chennevwin) 修复sdpa单通道attnmask的处理逻辑 修复ncnn2int8对仅有反量化的输出int8 scales保存崩溃问题 modelwriter支持tile层 ncnn2mem支持新的数组和字符串类型 x86上引用传参simd寄存器类型,函数无法接受对齐类型传值 检查gpu显存分配失败错误,返回错误码(@Upliner) simplevk支持查找高通windows vulkan驱动文件(@strongtz) simplevk支持apple平台动态加载vulkan驱动 simplevk支持VK_DRIVER_FILES环境变量加载vulkan驱动 禁用windows amd rdna2驱动的cooperative matrix软件模拟功能以提升性能 glslang更新到20260109 适配新windows-sdk的更多arm处理器特性检查功能 更新pybind 3.0.1,修复python-3.14使用pyncnn崩溃问题 更新pnnx到torch-2.9,支持onnx external data,支持dynamo-exported onnx pnnx支持转换torch.shrink Tensor.unflatten torch.flatten pnnx转换torch.flatten到ncnn支持多动态维度 pnnx支持转换F.interpolate nearest-exact pnnx修复转换Tensor.expand到ncnn缺失的repeats pnnx支持转换onnx gelu groupnorm rmsnorm gridsample pnnx支持合并更多transformer attention变种 pnnx支持合并更多sdpa attention变种 pnnx支持合并更多rmsnorm变种 pnnx合并连续permute,删除无用的permute pnnx添加deepseek_v3和qwen2 attention转换测试 pnnx合并非interleaved和更多的interleaved rope模块 pnnx合并t5风格的无gamma layernorm pnnx总是删除contiguous,view统一转为reshape pnnx转换onnx reshape丢弃allowzero参数 pnnx修复onnx旧版opset模型的部分shape折叠 pnnx修复折叠的常量输入丢弃逻辑 pnnx修复onnx padding非常量数值的转换 pnnx修复转换torch.stack负数axis越界崩溃问题 pnnx支持转换onnx动态resize pnnx合并相同常量为一个 pnnx改善paddle风格的tensor.size模式 pnnx改善合并whisper风格的attention pnnx自动从onnx模型中获取输入shape pnnx生成的推理代码在自动shape时生成有效shape pnnx改善pnnx.py中浮点数的表示方式 pnnx转换onnx模型不再输出无用的open failed警告 pnnx在pnnx.py中生成export_pnnx和export_ncnn工具函数 pnnx检查import xxx_pnnx路径,跳过目录检查(@glenn-jocher) 修复pnnx windows编译 ppocrv5分割英文文本时保留空格(@sxj731533730) 修复whisper例子中ffmpeg命令错误(@quink-black) whisper截断音频时长到30秒 新增arcface示例(@heabeounMKTO) gpu单元测试丢弃shape hint测试的pipeline缓存减少gpu显存占用 删除无用的testutil layer hook功能 新增gemm oom单元测试 ci比较二进制任务改用pull_request触发 ci修复windows-xp编译,统一workflow文件 ci更新mingw工具链下载地址 ci asan任务优化存储占用 ci新增aarch64 asan任务 ci更新macos-13到macos-15-intel(@Willaaaaaaa) ci更新windows-sdk和swiftshader 删除已停用的tencent ci(@mpj1234) 更新onnx模型转换文档 readme添加8bit量化文档链接(@mlbo) 编译步骤增加make install(@roachsinai) 添加打印VkMat内容的文档 新增Arduino UNO Q性能数据(@SimoSbara) 发布linux riscv64的python wheel 发布macos arm64的python pypy wheel
New Contributors
- @sxj731533730 made their first contribution in https://github.com/Tencent/ncnn/pull/6350
- @mpj1234 made their first contribution in https://github.com/Tencent/ncnn/pull/6355
- @glenn-jocher made their first contribution in https://github.com/Tencent/ncnn/pull/6379
- @Abandon-ht made their first contribution in https://github.com/Tencent/ncnn/pull/6393
- @Cat-myq made their first contribution in https://github.com/Tencent/ncnn/pull/6383
- @heabeounMKTO made their first contribution in https://github.com/Tencent/ncnn/pull/6386
- @SimoSbara made their first contribution in https://github.com/Tencent/ncnn/pull/6454
- @ihb2032 made their first contribution in https://github.com/Tencent/ncnn/pull/6460
- @chennevwin made their first contribution in https://github.com/Tencent/ncnn/pull/6472
- @0130w made their first contribution in https://github.com/Tencent/ncnn/pull/6286
- @chloeee99 made their first contribution in https://github.com/Tencent/ncnn/pull/6495
Full Changelog: https://github.com/Tencent/ncnn/compare/20250916...20260113