Commit Graph

307 Commits (33590b583f46a889a5071b8185b1b987559e5021)

Author SHA1 Message Date
Yan Chunwei 885c4e57ab
fea/infer memory optim2 (#14953)
6 years ago
Dun 9f8f0fc2d3 Memory optimization of depthwise conv op and group norm op (#15313)
6 years ago
tensor-tang d618e48309 fix fuse square mat order and refine test
7 years ago
tensor-tang a5d2a6d1ad add fuse pass of sequared mat sub fusion
7 years ago
tensor-tang ca6fdc6e33 refine and fix test
7 years ago
tensor-tang a89296ac1f add repeated fc relu pass
7 years ago
Zhaolong Xing 98e85f3735 add_transpose_flatten_concat_fuse (#15121)
7 years ago
tensor-tang c3a9f3c4b2 fix typo and refine
7 years ago
tensor-tang ab9c4b2a9f refine seqpool concat pass and remove unused nodes
7 years ago
tensor-tang ce909664d8 Merge remote-tracking branch 'ups/develop' into refine/seqpool/feed
7 years ago
flame fb63cd89d4
Add python ir graph API (#14917)
7 years ago
tensor-tang a0a27bd240 add seqpool concat fuse pass tester
7 years ago
tensor-tang 8e086a8521 follow comment and fix typo
7 years ago
tensor-tang 72d2a1801e add seqpool concat fuse pass
7 years ago
minqiyang b76695418a Polish log
7 years ago
minqiyang 4bfa110fd8 Add no lock optimize pass
7 years ago
Wu Yi e26cced7cc
refine batch merge pass (#14777)
7 years ago
Zhaolong Xing 4048cfa9da
Merge pull request #15048 from NHZlX/add_affine_channel_fuse
7 years ago
chengduo fe8495a758
[WIP] Refine MultiDevSSAGraph (#15040)
7 years ago
nhzlx a6aa8ea771 faster rcnn input is presistable. (fix it in paddle-trt)
7 years ago
hjchen2 956cf92145 Fix conv_elementwise_add2_act pass
7 years ago
nhzlx ce3782c193 add affine_channel fuse.
7 years ago
Tomasz Patejko e9eee0de6a MKLDNN residual connection fuse: fixing accuracy problem (#14874)
7 years ago
Zhaolong Xing a9fb34fad8
Merge pull request #14903 from NHZlX/add_conv_elementwise_pass
7 years ago
dzhwinter 7cd24b1318
add ir memory optimize. (#14530)
7 years ago
nhzlx c0c9fcd9c7 add source file
7 years ago
nhzlx 4e4a777243 add conv+elementwiseadd pass
7 years ago
Yan Chunwei a985949be9
Fea/fuse conv elementwise add fuse (#14669)
7 years ago
sneaxiy 7923042365 merge develop
7 years ago
Tao Luo 3243b45bb2
Merge pull request #14651 from luotao1/has_attr
7 years ago
Tao Luo 067ed70f2d add HasProtoAttr function in op_desc.h, clean node.h
7 years ago
Xin Pan 748549b2e3 Revert "Merge pull request #14798 from PaddlePaddle/revert-14786-revert-14782-revert-14398-imperative"
7 years ago
bingyanghuang 943ad4781f One possible solution to add flexibility for mkldnn placement pass (#14768)
7 years ago
Xin Pan c049fa7cf7
Revert "Revert "Revert "Imperative"""
7 years ago
Tao Luo c83d5b7a16
Merge pull request #14709 from yihuaxu/develop_4f71a6ee2_conv3d_bias_fusion_mkldnn_impl
7 years ago
Yihua Xu 3821fc3950 Merge branch 'develop' into develop_4f71a6ee2_conv3d_bias_fusion_mkldnn_impl
7 years ago
Yihua Xu 240d974ac5 Clean Code
7 years ago
Xin Pan 2538ef64f1
Revert "Revert "Imperative""
7 years ago
Xin Pan 6217f42ab7
Revert "Imperative"
7 years ago
Xin Pan b52f5d2870
Merge pull request #14398 from panyx0718/imperative
7 years ago
Xin Pan 0591ba96ec fix hack
7 years ago
sneaxiy 64ad051b9a merge develop
7 years ago
Yihua Xu 64e261c6cd Implement the fusion of convolution and bias for mkldnn
7 years ago
Tao Luo 8d6984eb9b change OpHasAttr to RuntimeHasAttr, add some comments
7 years ago
Xin Pan aeb74af54c allow operator to run imperatively
7 years ago
sneaxiy 096673f675 refactor eager deletion
7 years ago
Tao Luo c856ac8721 add OpHasAttr in node.h, update is_test_pass and mkldnn_placement_pass
7 years ago
minqiyang be04d99fe4 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into revert_vlog
7 years ago
minqiyang 53433d7f2e Revert the changes of VLOG
7 years ago
peizhilin 7c8c9dc9bf fix unit test cases
7 years ago