OpenI
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
1482 Commits
28 Branches
25 MB
3466 Download
Tree: 8da2f698a3
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '8da2f698a3'
${ noResults }
Commit Graph

386 Commits (8da2f698a37dd9a6dfc09efb7c190cd468a4fffa)

Author SHA1 Message Date
  Megvii Engine Team 8da2f698a3 feat(dnn/cuda): support warp perspective/pooling op when channel not aligned to 64 4 years ago
  Megvii Engine Team c218d4b029 feat(dnn/cuda): fallback conv qs4 support channel not aligend to 64 4 years ago
  Megvii Engine Team 4fe68ac9ed feat(dnn/cuda): support transforming layout between nchw and nchw64 when channel not aligned to 64 4 years ago
  Megvii Engine Team ae6ff2c5a6 feat(mgb/gopt): add opt pass for nchw64 layout transform 4 years ago
  Megvii Engine Team 56e863b7d4 fix(dnn/cuda): fix int4 epilogue stg bug 4 years ago
  Megvii Engine Team cff61a53d4 perf(dnn/cuda): optimize int4 sass conv main loop and epilogue without fuse_z 4 years ago
  Megvii Engine Team 12a0e61542 feat(dnn/cuda): add cuda elemwise int4 4 years ago
  Megvii Engine Team df1af59b5c feat(dnn): warp perspective support int4 4 years ago
  Megvii Engine Team 2398df079c feat(dnn/cuda): add cuda int4 pooling 4 years ago
  Megvii Engine Team 2a2a7f4552 test(mgb/opr): add testcase for conv bias int4 4 years ago
  Megvii Engine Team 858261af1f fix(python_module): fix conversion between numpy-ndarray and mgb tensor for qint4 and quint4 4 years ago
  Megvii Engine Team e250afb08f feat(dnn/cuda): support conv_bias for nchw64 and qint4 4 years ago
  Megvii Engine Team 3b9b87809d refactor(dnn): refactor lowbit tensor format 4 years ago
  Megvii Engine Team c74660ea88 fix(dnn/cuda): fix invalid local read for relayout format kernel 4 years ago
  Megvii Engine Team 8fef78d06d feat(dnn/cuda): add relayout format when width is an odd number 4 years ago
  Megvii Engine Team 91d6160769 feat(dnn/common): add tensor format for low-bits tensor layout 4 years ago
  Megvii Engine Team 19a554d674 test(dnn/cuda): add testcase for transforming tensor layout between nchw and nchw64 4 years ago
  Megvii Engine Team 71c2f61254 feat(dnn/cuda): add relayout format to support layout transform between NCHW and NCHW64 4 years ago
  Megvii Engine Team df009e89e1 feat(dnn/cuda): add cuda conv bias impls for NCHW format tensors with qint4 data type 4 years ago
  Megvii Engine Team ed92207585 feat(dnn/cuda): add conv bias impl for int4 data type using sass language 4 years ago
  Megvii Engine Team 52b55564d7 refactor(dnn/cuda): refactor reorder filter and bias kernel to support conv imma with data type s4 4 years ago
  Megvii Engine Team 517cc6846a ci(gitlab-ci): add inline lineno checking in copybara linter 4 years ago
  Megvii Engine Team 23032f50f2 feat(dnn/cuda): support float16 for index_incr_multi_axis_vec 4 years ago
  Megvii Engine Team 938944027d fix(mgb/dnn): fix cudnn8 convbias 4 years ago
  Megvii Engine Team 3591ef1f6a fix(mgb): fix conv cudnnconvbackwarddata algo witch is not shake 4 years ago
  Megvii Engine Team 1525a02530 feat(mge/module): add python wrapper for unfold 4 years ago
  Megvii Engine Team 13b15fb08c feat(megbrain): add correlation opr 4 years ago
  Megvii Engine Team 1997b1a289 feat(dnn/cuda): add correlation kernel 4 years ago
  Megvii Engine Team acb000d07f fix(api_cache): fix serialization for conv_desc 4 years ago
  Megvii Engine Team c4032222fa fix(api_cache): lock api cache for thread safety 4 years ago
  Megvii Engine Team 5419a95d1e perf(cuda/conv): cache serval cudnn api 4 years ago
  Megvii Engine Team 19887942c8 feat(dnn/apicache): add generic apicache 4 years ago
  Megvii Engine Team e4af4225ec fix(cmake): fix cmake depends 4 years ago
  Megvii Engine Team 6bb6787d9a feat(mge): add a tool which can analyze the file generated by compare_binary_iodump.py 4 years ago
  Megvii Engine Team c3f8cf04fa feat(dnn): add conv_bwd_data and conv_bwd_filter accuracy shake check 4 years ago
  Megvii Engine Team f36e99d30b fix(build): fix naive build 4 years ago
  Megvii Engine Team 0a86a07096 fix(mgb/dnn): fix cub potential issues 4 years ago
  Megvii Engine Team 1e6ef3771f feat(mgb/dnn): add accuracy shake checker 4 years ago
  Megvii Engine Team a5a29826dc feat(mgb/dnn): add accuracy_depend_on_batch attribute 4 years ago
  Megvii Engine Team 4b141f8de4 fix(mgb): add usable-depend-on-shape attr 4 years ago
  Megvii Engine Team 69a146c8c3 build(rocm): support rocm-3.9 4 years ago
  Megvii Engine Team a31b7c6ee3 build(rocm): partially support hcc compilation 4 years ago
  Megvii Engine Team 621ae0a1e8 fix(dnn): replace kernel launch syntax with macro for hcc 4 years ago
  Megvii Engine Team 78fff72a95 feat(dnn): add param_pack for rocm 4 years ago
  Megvii Engine Team 8163ed157d fix(dnn/cuda): fix cutlass matmul splitk limit 4 years ago
  Megvii Engine Team ef9aa80074 fix(mgb/dnn): fix cuda naive matmul algo 4 years ago
  Megvii Engine Team 2d18074a70 fix(mgb): fix spell error 4 years ago
  Megvii Engine Team ff755451d2 refactor(mgb): move algo's name from info to desc and delete some algo's unnecessary param() method 4 years ago
  Megvii Engine Team 756c1eb7f2 fix(mgb/dnn): add cuda float naive matmul algo 4 years ago
  Megvii Engine Team 8494a1529e chore(scripts): clarify and fix default value of bit combined enum 4 years ago