OpenI
/
MegEngine
Not watched
1
0
Fork 0
Code
Releases 31 Wiki Activity
Issues 0 Pull Requests 0 Datasets Model Cloudbrain
532 Commits
28 Branches
25 MB
4619 Download
Tree: 105e44504a
Branches Tags
${ item.name }
Create branch ${ searchTerm }
from '105e44504a'
${ noResults }
Commit Graph

161 Commits (105e44504ad5d9ff34bee48d5ac2bc0df33da0b6)

Author SHA1 Message Date
  Megvii Engine Team eb0cc59dcf feat(windows/python_whl/cuda): make windows MORE HAPPY for build whl with cuda 4 years ago
  Megvii Engine Team b44e0549b1 fix(mgb): add method to check local cuda env and refactor the way to get cuda include and lib dir 4 years ago
  Megvii Engine Team 22853fa20c feat(mge/quantization): add `mapping` parameter for custom modules 4 years ago
  Megvii Engine Team a7ff580e54 feat(mge/utils): add net stats to calculate parameters and flops 4 years ago
  Megvii Engine Team b43f6a2602 fix(mge/quantization): handle empty Observer in QATModule 4 years ago
  Megvii Engine Team 13e8f00a37 feat(mge/module): add forward hook support 4 years ago
  Megvii Engine Team ab9fa48ee7 feat(mge/quantization): make `q_dict` a kwarg rather than an arg 4 years ago
  Megvii Engine Team 7a8183f4e0 fix(mge/quantization): fix enable observer bug 4 years ago
  Megvii Engine Team 555ecea9bc feat(mge/quantization): add bias fakequant support 4 years ago
  Megvii Engine Team 9440842e27 fix(mge/core): fix Tensor deepcopy issue 4 years ago
  Megvii Engine Team d4b86b844e feat(mge/dtype): add int2 lowbit support and example 4 years ago
  Megvii Engine Team ef239f835f feat(windows/python_whl): make windows HAPPY for build megbrain python package 4 years ago
  Megvii Engine Team 35c712767d fix(mge/quant): fix TQT epoch scale change bug 4 years ago
  Megvii Engine Team e6e41242c7 fix(mge/quant): fix zero grad warn in TQT train 4 years ago
  Megvii Engine Team 4a01d23631 ci(mgb/python_module): fix doctest syntax error 4 years ago
  Megvii Engine Team 4495c0cc86 feat(mgb/quantization): add get quantize parameters support 4 years ago
  Megvii Engine Team 380cb6e47f feat(mge/jit): add support output symbol var name settings for dump 4 years ago
  Megvii Engine Team 134a102693 fix(mge/doc): fix typos, format 4 years ago
  Megvii Engine Team 7a8a2830a8 feat(quant): support nnie quant 5 years ago
  Megvii Engine Team 8269215959 fix(mge/module): fix named_children of Sequential 4 years ago
  Megvii Engine Team b689b4ce5c fix(mge/functional): add F.clamp to __all__ to fix docs 4 years ago
  Megvii Engine Team 177c268898 feat(osx/python_whl): fix python pytest failedon osx 4 years ago
  Megvii Engine Team b2f05bf8d8 fix(mge/module): fix quantized fold weight value range limit for fused conv/bn modules 4 years ago
  Megvii Engine Team 0df74604bd fix(data): fix contiguous id 4 years ago
  Megvii Engine Team c8f3742f0e fix(mge/doc): fix wrong doc for megengine doc 5 years ago
  Megvii Engine Team f856b17085 fix(mge/functional): reshape bias to (1, out_features) in linear 5 years ago
  Megvii Engine Team caf77d000e feat(mge/module): add quantize dtype load support for module load_state_dict 5 years ago
  Megvii Engine Team ef437f69aa fix(mge/data/dataloader): add refcount in _PlasmaStoreManager 5 years ago
  Megvii Engine Team 2b3a88d011 feat(mge/distributed): add parameter replica_mode 5 years ago
  Megvii Engine Team 6972fc7d75 feat(opr/standalone): import NMSKeep from MegSkull contrib 5 years ago
  Megvii Engine Team 5fa444c39a refactor(mge/quantization): add `narrow_range` to control quant dtype's lower bound 5 years ago
  Megvii Engine Team 6d367454cf feat(mge/opr-mm): add param local_grad for collective_comm opr 5 years ago
  Xu Xinran b532284cc2 chore(version): bump version. 5 years ago
  Megvii Engine Team af3de7e136 fix(jit): fix jit doc and add NCHW44_DOT 5 years ago
  Megvii Engine Team 7b8a99517c feat(mge/utils): export _internal.plugin to mge.utils 5 years ago
  Megvii Engine Team 6ed791bc86 feat(mge/quant): add TQT quant method 5 years ago
  Megvii Engine Team 328fb36f17 feat(mgb/opr-mm): add Scatter, Gather, AllToAll oprs 5 years ago
  Megvii Engine Team cc4e1dfd7c feat(mgb/compnode): expose mem_status and try_coalesce_all_free_memory to python 5 years ago
  Megvii Engine Team 7aeb4f6ca7 fix(mge/optimizer): use static key to avoid mem leak 5 years ago
  Megvii Engine Team ca52a93e9f fix(mge/quant): fix init value of histogram observer 5 years ago
  Megvii Engine Team 38f7cbd9aa fix(mge/module): fix redundant recursion in `train()` 5 years ago
  Megvii Engine Team 5c2323529d test(mge/quantization): add `quantize_disabled` related test 5 years ago
  Megvii Engine Team ab91302515 feat(mge/quantization): add `quantize_disabled` attribute in Module 5 years ago
  Megvii Engine Team 08ac685e3a feat(mge/functional): add logsumexp 5 years ago
  Megvii Engine Team 01092feb9b feat(mgb): add PackAllReducePass 5 years ago
  Megvii Engine Team c7e6c658fd refactor(mge/distribute): use is_root (and rank) in stead of rank and root at collective comm 5 years ago
  Megvii Engine Team b8d8886e35 refactor(mge/tensor): combine Dict and TensorDict 5 years ago
  Megvii Engine Team 7751a0676e docs(mge/tensor): add advanced index related docs 5 years ago
  Megvii Engine Team 6742a58b7e fix(quant): observer do not use cond_take 5 years ago
  Megvii Engine Team 35bc0e1f60 fix(mge/function): do not deeply copy saved tensor in Function 5 years ago