OpenI
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
938 Commits
28 Branches
25 MB
3465 Download
Tree: c225591476
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from 'c225591476'
${ noResults }
Commit Graph

201 Commits (c2255914762bdb78efcb01dcb9d8f994e3e33d41)

Author SHA1 Message Date
  Megvii Engine Team c225591476 chore(release): bump version 4 years ago
  Megvii Engine Team 2e87420865 fix(module): fix docs in normalization 4 years ago
  Megvii Engine Team 638ab52fdc feat(mge/imperative): simulates scalar 4 years ago
  Megvii Engine Team 7167fdbd49 feat(mge/module): add normalization module includes group_norm, instance_norm and layer_norm 4 years ago
  Megvii Engine Team 94dba16ff4 perf(mge/imperative): misc optimizations 4 years ago
  Megvii Engine Team 442058aead feat(mge/quantize): add batch matmul activation module for inference 4 years ago
  Megvii Engine Team 81e0dae4ac docs(mge): update GradManger docs 4 years ago
  Megvii Engine Team 6667100638 feat(mge): use weakref for GradManger.attach 4 years ago
  Megvii Engine Team 75ca5bfe65 feat(mge): remove GradManager.detach until it is ready 4 years ago
  Megvii Engine Team 544b798374 revert: feat(mge/grad_manager): add `clear_grad` method for GradManager 4 years ago
  Megvii Engine Team cc85047bf0 fix(mge/trace): fix sublinear in trace 4 years ago
  Megvii Engine Team b9918c329d feat(mge/distributed): support distributed key-value store 4 years ago
  Megvii Engine Team ab82c8da79 feat(mge/device): add python binding for get_mem_status_bytes 4 years ago
  Megvii Engine Team ab6328c563 feat(imperative): port persistent cache 4 years ago
  Megvii Engine Team 13272eaa63 fix(mge/trace): fix random op in symbolic trace 4 years ago
  Megvii Engine Team 1fed59293b perf(mge/optimizer): close conver_inputs for optimizer step 4 years ago
  Megvii Engine Team 495472954d fix(trace): link io-op to avoid deadlock 4 years ago
  Megvii Engine Team 33e8879af4 feat(mge/quantization): support distributed qat 4 years ago
  Megvii Engine Team 8e11204ab6 perf(mge/module): optimize conv_bn qat module to improve performance 4 years ago
  Megvii Engine Team 82b0f67770 fix(mge/core): fix dtype promotion issue for quantized dtype 4 years ago
  Megvii Engine Team 8118a5946d fix(mge/utils): fix get_oprs_seq of cgtools 4 years ago
  Megvii Engine Team ae8c3c8163 feat(mge/functional): add python wrapper for fake quant opr 4 years ago
  Megvii Engine Team 2e53077915 fix(mge/trace): use xpux device when dump 4 years ago
  Megvii Engine Team 9cb3c07cd4 feat(mge/functional): add elemwise mode support string input 4 years ago
  Megvii Engine Team 8fad00a158 feat(mge/functional/nn): add conv1d padding 4 years ago
  Megvii Engine Team 094601e834 feat(mge/distributed): allow remote grad by using grad manager 4 years ago
  Megvii Engine Team 02438ee635 refactor(mge/distributed): use thread.Threading to create Server 4 years ago
  Megvii Engine Team a1efd4d56d fix(mge/parampack): fix param pack when no param left 4 years ago
  Megvii Engine Team e0e1896450 docs(mge): formatting math in docstring 4 years ago
  Megvii Engine Team 28dbadf729 feat(imperative): add remap opr 4 years ago
  Megvii Engine Team 1e0fb127d1 perf(mge/functional): reduce matmul python overhead 4 years ago
  Megvii Engine Team 7cd846a570 fix(mge/batch_norm): fix batch_norm check when trace(symbolic=True) 4 years ago
  Megvii Engine Team c89209450d ci(mge): remove blank line for windows doctest 4 years ago
  Megvii Engine Team e082e27780 refactor(mge/data): Refactor megeninge.data.dataset 4 years ago
  Megvii Engine Team f04e0d777e feat(mge/data): dpflow dataset, stream sampler and loader 4 years ago
  Megvii Engine Team be511a56f9 fix(mge/imperative): fix tensor astype failed for quantized type 4 years ago
  Megvii Engine Team b309890c66 docs(mge): pytest for sphinx docstring 4 years ago
  Megvii Engine Team 1b56851715 fix(mge/trace): fix graph option in trace 4 years ago
  Megvii Engine Team 1217801133 perf(mge): add opdef for broadcast 4 years ago
  Megvii Engine Team fccb2510c4 perf(mge): add opdef for elemwise and batchnorm 4 years ago
  Megvii Engine Team b327822994 feat(mge/grad_manager): add `clear_grad` method for GradManager 4 years ago
  Megvii Engine Team 2627e1f7df fix(mge/grad_manager): allow multiple calls of `release` 4 years ago
  Megvii Engine Team 3af1056377 feat(mge/grad): attach grad immediately 4 years ago
  Megvii Engine Team d8ac6c70a1 fix(quantize): fix quantize calibration dtype issue 4 years ago
  Megvii Engine Team 50d64bd333 fix(pytest/windows/impertive): open impertive pytest on windows 4 years ago
  Megvii Engine Team 786399c5c9 fix(pytest/windows/impertive): fix impertive pytest failed on windows 4 years ago
  Megvii Engine Team 1fa143ce87 refactor(mge/functional): matmul supports symbolic shape, batched mv multiply 4 years ago
  Megvii Engine Team 95f6b53183 feat(opr/nvof): add nvof operator 4 years ago
  Megvii Engine Team 9748aebeea refactor(mge): tensor_shape -> symbolic_shape 4 years ago
  Megvii Engine Team 8acc3acf70 fix(mge/functional): do not del anything 4 years ago