Commit Graph

174 Commits (d78e8f23a6c469766315e863da7aa1531ab0d491)

Author SHA1 Message Date
Qiao Longfei d78e8f23a6 code format
7 years ago
Qiao Longfei bf9764898d add TestEmptyPserverOptimizeBlocks
7 years ago
Qiao Longfei a11d4f300e use len instead of size for python list
7 years ago
Qiao Longfei fa84ba2350 set en empty optimize block if pserver has no optimize block
7 years ago
Qiao Longfei d26ff8cb2d Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into cpu-for-1.1-merge-with-shape
7 years ago
Wu Yi 26200f2e42
[1.1] [project] train imagenet using large batch size (#13766)
7 years ago
Qiao Longfei 641369f92b Merge branch 'dist-table-do-not-init-on-trainer' of ssh://github.com/jacquesqiao/Paddle into cpu-for-1.1-merge
7 years ago
Qiao Longfei f1a3fb041b Merge branch 'fix_lookuptable_in_reduce' of https://github.com/seiriosPlus/Paddle into cpu-for-1.1-merge
7 years ago
tangwei12 5ce3a32e06
Merge branch 'develop' into optimizer-prefetch
7 years ago
seiriosPlus b6590b05fb submit by tangwei12, test=develop
7 years ago
Qiao Longfei 93f173db7d code format test=develop
7 years ago
Qiao Longfei a13c788a04 fix a bug
7 years ago
Qiao Longfei d52fcaf42e replace table init op with fake init
7 years ago
Qiao Longfei 8fe90cbdb1 Merge branch 'develop' of https://github.com/PaddlePaddle/Paddle into dist-table-do-not-init-on-trainer
7 years ago
Qiao Longfei 4673fea551 trainer startup should not init table optimizer because it maybe large
7 years ago
Xin Pan 4cd44c00c5 fix
7 years ago
Xin Pan 38cf553108 fix distributed
7 years ago
tangwei12 48982e9dc7 fix lookuptable in reduce strategy
7 years ago
tangwei12 fa2ab3346c
fill constant add infervarshape, lookuptable clone lr var (#13830)
7 years ago
Wu Yi 77e9339deb
fix api get_pserver_programs (#13820)
7 years ago
Wu Yi 18e5dccc0b
Merge pull request #13619 from typhoonzero/fix_graph_num
7 years ago
typhoonzero 5b152b1fac fix graph num
7 years ago
tangwei12 97cf1eb6d7
Add distributed unit tests about text_classification/simnet-bow/ctr (#12812)
7 years ago
Wu Yi 1ab7b55162
Merge pull request #13602 from typhoonzero/add_dist_decayed_adagrad_op_support
7 years ago
tangwei12 85362e98dd
Batch AUC (#13567)
7 years ago
Wu Yi 16e73e0d28
hide operator API (#12543)
7 years ago
typhoonzero 75258c79bf add decayed_adagrad support for dist train
7 years ago
Qiao Longfei cce056cad1
Merge pull request #13537 from jacquesqiao/fix-table-optimize-send-op
7 years ago
Wu Yi aeb2dc2b05
Nccl2 dist API (#13506)
7 years ago
qiaolongfei f4219c0d1d fix table grad send sync_mode
7 years ago
Wu Yi 29c63d180f
[Feature] dist op role and lr op role, to support memory optimize with dist training (#13220)
7 years ago
Wu Yi efafc72f62
Hide program APIs (#12315)
7 years ago
Qiao Longfei 020d13c18a
fix dist table send hang problem (#13259)
7 years ago
Wu Yi 3ab3a7f392
Trainer auto wait pserver ports (#13341)
7 years ago
minqiyang c838fa3173 Port dist_transpiler to Python3.5
7 years ago
tangwei12 ff618a2880 bug fix
7 years ago
qiaolongfei f1554a4a07 fix sparse grad merge on pserver
7 years ago
Wu Yi 0b8067c0dc
fix dist train reduce mode (#13068)
7 years ago
Wu Yi 9ae55dd70d
fix dist transpile with memopt (#12974)
7 years ago
Wu Yi 0ee6fed05b
Refine dist rpc deps (#12899)
7 years ago
minqiyang 312f3b8654 Fix random diff between python2 and python3
7 years ago
Wu Yi b8da70c370
Resovle multi gpu async deps (#12828)
7 years ago
tangwei12 cbc6e6eb97
Merge pull request #12247 from seiriosPlus/dis_ckpt_fix
7 years ago
Qiyang Min 72965226e6
Merge pull request #12818 from velconia/fix_python3_CI_job
7 years ago
Wu Yi f63368db5e
Add async dist tests (#12798)
7 years ago
tangwei12 7dbf5f1244
Update distribute_transpiler.py
7 years ago
minqiyang beb93bb901 Fix ut bug for graph_test
7 years ago
tangwei12 5fa1f05c9d code clean and rename
7 years ago
tangwei12 bf2f1599f9 code clean
7 years ago
tangwei12 dbb4f0d35d Merge branch 'develop' of github.com:PaddlePaddle/Paddle into dis_ckpt_fix
7 years ago