OpenI
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
2268 Commits
28 Branches
25 MB
3779 Download
Tree: v1.7.2.m1
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'v1.7.2.m1'
${ noResults }
Commit Graph

560 Commits (v1.7.2.m1)

Author SHA1 Message Date
  Megvii Engine Team 8cb201868e fix(mgb): fix fastrun cache serialization method 3 years ago
  Megvii Engine Team 563239d38f feat(dnn): add arm_common nchw44 cwconv3x3s1p1 and cwconv5x5s1p2 3 years ago
  Megvii Engine Team 3344b580a9 feat(dnn): add elemwise for nchw88+fp16 3 years ago
  Megvii Engine Team 682c74df27 feat(dnn): add direct nchw88 fp16 conv 3 years ago
  Megvii Engine Team fca195351c feat(gopt): add nhwc fuse conv typecvt optpass 3 years ago
  Megvii Engine Team 2fc7358517 Revert "feat(dnn/apicache): add generic apicache" 3 years ago
  Megvii Engine Team de363c04af Revert "perf(cuda/conv): cache serval cudnn api" 3 years ago
  Megvii Engine Team 729ee64988 Revert "fix(api_cache): lock api cache for thread safety" 3 years ago
  Megvii Engine Team 64c922c4bb Revert "fix(api_cache): fix serialization for conv_desc" 3 years ago
  Megvii Engine Team 3d3666b6e0 test(dnn/bn): add compatible configs for NHWC BN 3 years ago
  Megvii Engine Team b3e54eade1 feat(dnn/bn): use new cudnn BN kernel to support NHWC 3 years ago
  Megvii Engine Team 3977b7aa0b feat(mgb/shuffle): add shuffle opr 3 years ago
  Megvii Engine Team 17371e79b9 fix(dnn/reduce): fix reduce_mean o16c32 is incorrect for large tensor 3 years ago
  Megvii Engine Team eca6e1d931 fix(ci): fixes for ci 3 years ago
  Megvii Engine Team c14e5719f8 feat(mgb/gopt): add profile impl for global layout transform pass 3 years ago
  Megvii Engine Team 8a3eb05a1b refactor(mgb/gopt): refactor tensor reformat opt pass 3 years ago
  Megvii Engine Team c33126ab5c feat(mgb/gopt): add reformat manager 3 years ago
  Megvii Engine Team 4f28e14684 fix(dnn): fix compatibility broken of convolution format 3 years ago
  Megvii Engine Team 8b40f57738 feat(mgb/dnn): add conv1x1 algo for matrix mul 3 years ago
  Megvii Engine Team fb49a2834f refactor(mgb/dnn): refactor enum used in serializing 3 years ago
  Megvii Engine Team d69b59035d feat(dnn): add an get_all_algorithms_safe interface 3 years ago
  Megvii Engine Team 103d7f33ba refactor(dnn/rocm): update hip license header 4 years ago
  Megvii Engine Team 5aa52d3863 feat(dnn/rocm): add adaptive pooling opr 3 years ago
  Megvii Engine Team 83cf4ee64e refactor(dnn/rocm): remove some useless includes 3 years ago
  Megvii Engine Team 323a4642e6 feat(dnn/rocm): add topk opr 3 years ago
  Megvii Engine Team f4784f4af1 feat(dnn/rocm): add argsort opr 3 years ago
  Megvii Engine Team 6082c353e7 feat(dnn/rocm): support bool in type_cvt and elemwise 4 years ago
  Megvii Engine Team 8b94f49328 fix(dnn/cuda): fix elemwise and relayout int4 bug when last shape is 1 3 years ago
  Megvii Engine Team 694aa1bd92 feat(dnn): add heuristic cache 3 years ago
  Megvii Engine Team bc9cfc277a feat(mgb): add arm resize nchwxx and naive nearest interp 3 years ago
  Megvii Engine Team 722aecd437 feat(mgb): support fp16 nhwc backward 3 years ago
  Megvii Engine Team 0708bc780c fix(dnn/cuda): disallow implicit dtype conversion in cublaslt matmul algos 3 years ago
  Megvii Engine Team 1e83ab638e feat(dnn): add channelwise conv for fp16 nchw88 3 years ago
  Megvii Engine Team 7b855dc64a fix(dnn/cuda): fix compilation for windows bazel 3 years ago
  Megvii Engine Team 3abe0b2462 fix(mgb): fix rocm pooling 3 years ago
  Megvii Engine Team 16678bb998 fix(dnn): fix_short_cutlass_name_gemm 3 years ago
  Megvii Engine Team 4c13bc7e1b feat(dnn/cuda): add nhwc int8 deconv 3 years ago
  Megvii Engine Team 11f022ff7c feat(dnn/cuda): add nhwc int8 imma conv and conv fuse typecvt 3 years ago
  Megvii Engine Team a0231a7920 fix(dnn/cuda): fix algo matmul for conv bwd filter 3 years ago
  Megvii Engine Team 56c1b626bf refactor(dnn): move arch-dependant code to arch.h 3 years ago
  Megvii Engine Team 67575d582c feat(mge/opr): add interpolate bilinear mode 3 years ago
  Megvii Engine Team 0558b2123d feat(mge/opr): add interpolate nearest mode 3 years ago
  Megvii Engine Team 127870a926 feat(dnn/opencl): add heuristic rule for batched matmul 3 years ago
  Megvii Engine Team c25125e3d2 perf(dnn/cuda): sass int8 epilogue remove shared load 3 years ago
  Megvii Engine Team 55efc8e197 feat(mgb/gopt): add reformat emitter 4 years ago
  Megvii Engine Team c9d060307f feat(dnn/common): add named tensor shape 4 years ago
  Megvii Engine Team ff0e6be7b9 fix(dnn/cuda): fix cutlass tensorop kernels 3 years ago
  Megvii Engine Team 336761253d feat(dnn/cuda): add tensorcore matmul for fp16 data type 3 years ago
  Megvii Engine Team 2c4ee99227 fix(dnn): short cutlass filename in windows 3 years ago
  Megvii Engine Team 432592374d build(dnn/cuda): fix cmake compile dependency for cutlass kernels 3 years ago