root
/
MNN
mirror of https://github.com/alibaba/MNN.git
1
0
Fork 0
Code Issues Actions 1 Packages Projects Releases Wiki Activity
1,325 Commits 20 Branches 109 Tags 396 MiB
Commit Graph

549 Commits

Author SHA1 Message Date
xiaying 0d1f5fcf72 Fix bug for MatMulExecution 2023-03-25 10:02:06 +08:00
xiaying a931d40ddc Optimize for one-broadcast matmul 2023-03-25 10:02:06 +08:00
xiaying 4935bfc1ae Optimize cuda gather for region x,y,z large 2023-03-25 10:02:06 +08:00
xiaying 7629ba674e [MNN:Sync] Sync Internal 2.4.1 2023-03-20 11:32:29 +08:00
Zeekim a92de8a5bc fix(opencl): fix mLWS dimension bigger than gws 2023-03-08 11:22:52 +08:00
xiaying 4e2ad365e8 [MNN:Sync] Sync Internal Gitlab 2023-02-28 10:41:24 +08:00
王召德 86080f24c1
Merge pull request #2226 from DaydreamCoding/feature/fix_msvc_bf16 
MSVC adapt for BF16
 2023-02-17 10:09:56 +08:00
xiaying 4a609006eb [MNN:Sync] Sync Internal 2.3.1 2023-02-15 10:30:27 +08:00
zhaode.wzd 03008e04b7 fix&add package_scripts 2023-01-11 17:33:00 +08:00
zhaode.wzd b142695010 [Sync] Sync Internal changes. 2023-01-11 15:08:58 +08:00
xiaying d46b6b998d [MNN:Sync] Sync Internal 2.3.0 2022-12-30 15:18:58 +08:00
xiaying b1f5664ced [MNN:Internal] Sync to 2.2.3 2022-12-24 09:42:39 +08:00
xiaying ad5d243c9f [MNN:Sync] A few bugfixes 
1. 支持 Onnx If 空子图的情况（这种情况是条件判断一定为真或假）
    2. 修正 Where 算子在 zeroshape 下维度计算出错的问题
    3. 修正 Reduce 计算 zeroshape 的非 prod 情况
    4. 修正 arch64-linux 上编译错误
    5. 修正 头文件 NNAPI 的注释错误
    6, 部分训练相关问题修正
 2022-12-04 15:17:36 +08:00
xiaying 8908e80d44 [Sync] Sync Internal 2.2.2 2022-11-18 22:35:31 +08:00
zhaode.wzd c683c5c6c2 [Sync] Sync Internal Gitlab 2.2.1 2022-11-08 17:05:14 +08:00
xiaying acb3bb6c62 [Sync] Sync Internal Gitlab 2.2.0 2022-10-30 08:44:24 +08:00
xiaying aa25623600 Fix bug for remain area for GridSampler 2022-10-13 11:13:19 +08:00
xiaying db53f951e6 [Sync] Sync Internal 2.1.2 2022-09-30 10:02:52 +08:00
wtiandong 2768a397bd Merge remote-tracking branch 'origin/master' into interp3D 2022-09-27 17:13:37 +08:00
wtiandong 9e284352b5 merge interp3d_op_param into interp_op_param 
merge interp3d_op_param into interp_op_param
 2022-09-27 17:07:23 +08:00
jxt1234 a5ed4942e8
Merge pull request #2079 from jokerz0624/accelerate/TensorConvert 
accelerate MNNPackTranspose
 2022-09-27 09:59:54 +08:00
zw22zw22 634474cc85 fix bugs for leakrelu in hiai ir for mnn ir 2022-09-27 07:53:27 +08:00
jokerz0624 71d0975d37 improvement(TensorConvert): accelerate MNNPackTranspose with SIMD when channel=3 2022-09-24 16:49:20 +08:00
zw22zw22 299525c7c7 fix binaryOP bugs 
fix compiling error for hiai
 2022-09-23 16:05:08 +08:00
jxt1234 f001a65c81
Merge pull request #2051 from DaydreamCoding/patch-12 
Fix ThreadPool behavior
 2022-09-19 10:47:41 +08:00
jokerz0624 62d529379b feat(iOS/macOS): add Apple A16 and M2 support in CPU family 2022-09-18 12:58:17 +08:00
DaydreamCoding d5e08a913f Fix ThreadPool behavior : Pipeline::encode may anr when other session call ThreadPool::active() 
Pipeline::encode -> GeometryComputerUtils::shapeComputeAndGeometryTransform -> onExecute
 2022-09-08 14:37:31 +08:00
wtiandong 71aae927ff Add Interp3D Support 
1. add PyTorch interpolation 3D to Onnx to MNN converter
2. add interpolation3D nearest CPU/OpenCL implementation

all added OPs are verified
update opencl_program.cc

update opencl_program.cc
 2022-09-07 15:56:08 +08:00
jxt1234 41db47f2c6
Merge pull request #2038 from DaydreamCoding/patch-11 
Fix VecHalf.hpp not include neon header
 2022-09-05 10:33:40 +08:00
jxt1234 5fbfa5a1d7
Merge pull request #2032 from MambaWong/master 
Fix compile errors caused by "#define MNN_THREAD_LOCK_CPU"
 2022-09-05 10:29:58 +08:00
DaydreamCoding 206f73eda7
Update VecHalf.hpp 
fix header include
 2022-09-01 15:33:13 +08:00
xiaying fafafef5c5 [MNN:Sync] Sync Internal 2.1.0 2022-08-31 20:11:16 +08:00
jason_w 282e771445
Fix compile errors caused by "#define MNN_THREAD_LOCK_CPU" 
error: sort is not a member of std
error: gettid was not declared in this scope
error: __NR_sched_setaffinity was not declared in this scope
error: syscall was not declared in this scope
 2022-08-25 12:25:30 +08:00
zhaode.wzd 76b8ace520 Sync Internal 2.0.5 2022-08-23 21:21:29 +08:00
xiaying 68708c5d66 Sync Internal 2.0.4 2022-08-12 10:30:48 +08:00
xiaying 8330da263a [Sync] Sync internal 2.0.3 2022-07-22 09:59:30 +08:00
xiaying eb51926f84 [MNN:Sync] Sync internal Gitlab to 2.0.2 2022-07-19 13:52:07 +08:00
xiaying 3cf5126828 Fix compute error for fp16 convolution dw 2022-07-15 12:47:48 +08:00
xiaying 8e0f544ea6 Fix Remain treat bug for AVX512-Int8 2022-07-15 12:47:48 +08:00
xiaying 89288cc509 Update README.md, fix CPU Runtime compile bug for Android - armv8.2 2022-07-12 12:43:06 +08:00
jxt1234 7102b4890b
Merge pull request #1821 from snadampal/aarch64_linux_fp16 
backend: cpu: runtime: linux aarch64 hwcaps setting for ARMV82
 2022-07-12 11:32:18 +08:00
Brian Li 2801621ea5 Add missing headers 2022-07-12 01:28:27 +08:00
xiaying 2ec9495719 [MNN:Sync] Sync 2.0. 2022-07-11 10:56:37 +08:00
hebin 4679f848c4 fix windows compile on avx512 2022-06-29 16:43:49 +08:00
雁行 6cf30db8f6 Opt DepthToSapce from raster to coreml execution. 2022-06-29 14:59:46 +08:00
xiaying c02c8cc145 Fix compile bug for ios simulator for m1 2022-06-28 14:10:51 +08:00
xiaying 2d13d6a495 2022-06-27 10:52:11 +08:00
xiaying d3ffdf4229 [MNN:Sync] Sync internal gitlab 2022-06-24 18:30:05 +08:00
xiaying aeaac3fde3 [MNN:Sync] Sync internal gitlab 2022-06-10 10:39:50 +08:00
xiaying c5592d284b Fix bug for buffer not alloc enough 2022-06-09 15:57:17 +08:00