wangwei
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
1971 Commits
28 Branches
25 MB
424 Download
Tree: ec75cd867b
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'ec75cd867b'
${ noResults }
Commit Graph

1971 Commits (ec75cd867bead83144bb3860c73aba6bb7e1fa1d)
 

Author SHA1 Message Date
  Megvii Engine Team aa20404027 feat(lite): add lite static all in one 4 years ago
  Megvii Engine Team a0231a7920 fix(dnn/cuda): fix algo matmul for conv bwd filter 4 years ago
  Megvii Engine Team f3ed59d336 feat(dnn/opencl): add heuristic rule for elemwise 4 years ago
  Megvii Engine Team 29d24dbb80 fix(mge/function): fix interpolate unsupport fp16 error 4 years ago
  Megvii Engine Team 36df3850f3 test(mgb): remove the padding random test case 4 years ago
  Megvii Engine Team e21967bb40 feat(mge): add env MGE_FASTRUN_CACHE_DIR 4 years ago
  Megvii Engine Team 6a1ec8a890 feat(mge): add git commit-id into fastrun cache key 4 years ago
  Megvii Engine Team ae87876d34 feat(mge): refactor weightscaler 4 years ago
  Megvii Engine Team 5d9ac970ab fix(mgb): fix fastrun compnode 4 years ago
  Megvii Engine Team 56c1b626bf refactor(dnn): move arch-dependant code to arch.h 4 years ago
  Megvii Engine Team 67575d582c feat(mge/opr): add interpolate bilinear mode 4 years ago
  Megvii Engine Team 0558b2123d feat(mge/opr): add interpolate nearest mode 4 years ago
  Megvii Engine Team 171d69155a fix(fp16): fix midout build issue when hit fp16 trace 4 years ago
  Megvii Engine Team 127870a926 feat(dnn/opencl): add heuristic rule for batched matmul 4 years ago
  Megvii Engine Team d86ed426ee fix(dtr): simulate the system stack to avoid stack overflow during recomputing 4 years ago
  Megvii Engine Team c25125e3d2 perf(dnn/cuda): sass int8 epilogue remove shared load 4 years ago
  Megvii Engine Team bc2b1690c9 ci(thirdparty): add third_party cache 4 years ago
  Megvii Engine Team 6070f1272d fix(mgb): fix getting static memory alloc info 4 years ago
  Megvii Engine Team e8a5932d1e perf(mgb/gopt): optimize impl of reformat builders 4 years ago
  Megvii Engine Team 58b8b14554 refactor(mgb/gopt): add checker for reformat emitter 4 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 4 years ago
  Megvii Engine Team 336761253d feat(dnn/cuda): add tensorcore matmul for fp16 data type 4 years ago
  Megvii Engine Team 12cdbddd14 fix(ci): clean fastrun cache in windows and macos ci 4 years ago
  Megvii Engine Team 31705913c0 fix(ci): set MGE_FASTRUN_CACHE_TYPE=FILE in ci env 4 years ago
  huangxinda f814a4ae78 ci(mge): update test script 4 years ago
  Megvii Engine Team 2c4ee99227 fix(dnn): short cutlass filename in windows 4 years ago
  Megvii Engine Team b17b56f309 fix(build): fix copy bara error 4 years ago
  Megvii Engine Team 3c6665f7c1 feat(lite/whl): merge lite whl to main package 4 years ago
  Megvii Engine Team 989fdde255 refactor(subgraph): use graph queue to cache compiled op graphs 4 years ago
  Megvii Engine Team a7a3bf2d6c test(subgraph): simple test for subgraph 4 years ago
  Megvii Engine Team d063d5774f perf(functional): use fma to reduce elemwise but disable subgraph compilation 4 years ago
  Megvii Engine Team 2a063f8e87 fix(subgraph): fix scope mismatch of subgraph content 4 years ago
  Megvii Engine Team 3206af9db2 perf(functional/matmul): reimplement matmul with subgraph 4 years ago
  Megvii Engine Team 8c47c1f149 perf(syncbn): reimplement with subgraph 4 years ago
  Megvii Engine Team 53da5c79f4 feat(cg): add comp_seq_sync_device option 4 years ago
  Megvii Engine Team e1c7b22ff0 perf(ops): enable memory forward for reduce in special cases 4 years ago
  Megvii Engine Team cd60d26852 perf(ops): specialize Broadcast 4 years ago
  Megvii Engine Team 3fd3e000d1 feat(ops): add serval utility ops 4 years ago
  Megvii Engine Team 5b4f7c5dd0 perf(interpreter): unwind ops with make_forward_graph 4 years ago
  Megvii Engine Team 5798f6ce20 feat(subgraph): add OpMeth make_forward_graph 4 years ago
  Megvii Engine Team 48db45d123 perf(interpreter): try put device value with host to reduce d2h 4 years ago
  Megvii Engine Team a605f38b26 refactor(opmeth): add OpMethCache struct 4 years ago
  Megvii Engine Team 0213dbe556 feat(subgraph): add graph builder 4 years ago
  Megvii Engine Team 0b8dc2c98b refactor(subgraph): add generic encoded_graph 4 years ago
  Megvii Engine Team 88b3c84229 refactor(subgraph): move to subgraph.h 4 years ago
  Megvii Engine Team 43a9e6e361 fix(third-party): extra logs 4 years ago
  Megvii Engine Team 432592374d build(dnn/cuda): fix cmake compile dependency for cutlass kernels 4 years ago
  Megvii Engine Team 1e3af4dd17 fix(mgb/comp_node): add more info in `comp_node.to_string()` 4 years ago