Commit graph

103 commits

Author SHA1 Message Date
Swetha Mandava
daaab9ea6a
update run_classifier.py typo 2020-05-18 12:19:01 -07:00
Swetha Mandava
58763147ff fixing xla fragmentation in latest container 2020-05-18 10:25:13 -07:00
Swetha Mandava
bd5ce85888 Updating notebooks to have relative paths instead of absolute 2020-05-18 10:24:28 -07:00
Swetha Mandava
942b09611c change default dllog path, disable horovod for 1 gpu 2020-05-14 14:25:37 -07:00
Swetha Mandava
cfc2395057 merge conflicts 2020-05-13 10:54:53 -07:00
Swetha Mandava
398dc781a1 amp env variable to amp api 2020-05-12 22:18:05 -07:00
Swetha Mandava
58a3ed6bab trtis to triton update 2020-05-12 22:17:33 -07:00
PrzemekS
8fecbe7ca7
Merge pull request #420 from rajeevsrao/dev/master-trt-bert-7.0
BERT demo integration for TensorRT-7.0
2020-05-11 19:58:48 +02:00
Swetha Mandava
b7903f0f62 Inference throughput computation removing outliers, eval when eval script is given only 2020-04-29 14:17:22 -07:00
Swetha Mandava
c94b73f9ea Adding DLLogger and specificying v1.1 in the readme results for clarity 2020-04-24 14:01:53 -07:00
Rajeev Rao
33112129c5 Fix docker build script 2020-04-23 15:40:50 -07:00
Rajeev Rao
c608b656ea Python notebook fixes 2020-04-20 17:35:20 -07:00
Rajeev Rao
d0466c06ce Update performance data for BERT-7.0 2020-04-20 17:35:20 -07:00
Rajeev Rao
ba2840dcf9 Update TensorRT Dockerfile 2020-04-20 17:35:20 -07:00
Rajeev Rao
af69862cfb Remove deadcode in TensorRT builder
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
2020-04-20 17:35:20 -07:00
Rajeev Rao
899c9988f7 Fix BERT/TRT-7.0 regressions
- Revert network to use fcPlugin and geluPlugin

Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
2020-04-20 17:35:20 -07:00
Rajeev Rao
5cac8bcee4 Address review comments
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
2020-04-20 17:35:20 -07:00
Rajeev Rao
56a8c20b6b Fix TRT base container version in README
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
2020-04-20 17:35:20 -07:00
Rajeev Rao
0c42d181b7 BERT demo integration for TensorRT-7.0
Signed-off-by: Rajeev Rao <rajeevrao@nvidia.com>
2020-04-20 17:35:20 -07:00
Przemek Strzelczyk
4f0f43b9a5 Adding Transformer-XL/TF 2020-04-08 15:21:57 +02:00
Swetha Mandava
c57e4d2b08 readme fixes 2020-04-03 15:02:45 -07:00
Sharath T S
6227f32700
[BERT/PyT] Fix dataprep for NSP labels (#426) 2020-03-23 14:59:54 -07:00
PrzemekS
96b6e67084
Merge pull request #311 from haamis/master
Fix `eval_files_dir` requirement.
2020-03-09 12:52:36 +01:00
Swetha Mandava
0845aaa901
[BERT/TF] bug fix in beta bias correction terms (#395) 2020-02-06 22:08:20 -08:00
Przemek Strzelczyk
cef4bab3fc Adding BERT/TF Inference with TensorRT; minor README fixes 2020-02-05 14:21:13 +01:00
Swetha Mandava
784eb0d8ca [BERT/TF] trtis dependency fix (#373) 2020-01-13 13:37:36 -08:00
Swetha Mandava
d08f065c0c Merge branch 'master' of https://github.com/NVIDIA/DeepLearningExamples into smandava/readme_edit 2020-01-03 10:44:47 -08:00
Swetha Mandava
d567f0e9e1 mismatch numbers 2020-01-03 10:42:04 -08:00
Swetha Mandava
23d56b7cee replacing / with - in init_checkpoint string for printing 2019-12-13 19:00:40 -08:00
Chris Forster
0ebeb8f12d
Update README.md 2019-12-13 12:56:19 -08:00
Swetha Mandava
b4384a51e3 readme fix 2019-12-13 07:48:39 -08:00
PrzemekS
5ae555a190
Typo in Dockerfile 2019-12-06 14:44:00 +01:00
Swetha Mandava
e9d9372ce7
Update Dockerfile 2019-11-27 22:25:21 -08:00
Swetha Mandava
c4061ebb09
Merge branch 'master' into master 2019-11-25 10:40:01 -08:00
Antti Virtanen
a9019db534
Fix eval_files_dir requirement.
Changed run_pretraining.py to not require `--eval_files_dir` if not doing eval.
2019-11-20 16:50:35 +02:00
nvpstr
a387db4708
Merge pull request #292 from khcs/master
fix a minor typo on BioBERT README.
2019-11-19 10:12:04 +01:00
nvpstr
55c5f99f59
Merge pull request #286 from eric-haibin-lin/patch-1
Fix a typo
2019-11-19 10:07:01 +01:00
Swetha Mandava
2a93a1efa9 mkdir missing 2019-11-18 18:49:02 -08:00
Przemek Strzelczyk
a70896405d Updating BERT/PyT
* Use LAMB from APEX
* Code cleanup
* Bug fix in BertAdam optimizer
2019-11-18 23:07:24 +01:00
Swetha Mandava
59b89880e3 allow_growth_fix=True removed 2019-11-13 11:06:15 -08:00
Hoo Chang Shin
92e52384f2 fix minor typo in README. 2019-11-13 11:38:41 -05:00
Hoo Chang Shin
caece99944 fix minor typo on README. 2019-11-13 11:36:49 -05:00
Hoo Chang Shin
536a5cfffc fix minor typo on README. 2019-11-13 11:29:57 -05:00
Hoo Chang Shin
70c51ad7f8 Merge remote-tracking branch 'upstream/master' 2019-11-13 11:28:26 -05:00
Swetha Mandava
b2466a0004
mismatch columns in readme 2019-11-12 13:55:16 -08:00
Haibin Lin
1ae1592ef8
Update optimization.py 2019-11-11 10:11:37 -08:00
Swetha Mandava
e94c6936e4
Merge pull request #3 from lapolonio/patch-3
Update Dockerfile
2019-11-08 11:24:03 -08:00
Leonardo Apolonio
826fcd4d33
Update Dockerfile
add libcurl3 install required by python when importing tensorrtserver.api module
2019-11-08 10:17:58 -05:00
Leonardo Apolonio
46a3d6e1de
Update run_trtis.sh
default trtis_model_name in run_trtis.sh should be consistent with export_model.sh
2019-11-08 10:15:53 -05:00
Swetha Mandava
e873db23cd moving trtis to 19.08 2019-11-07 13:07:47 -08:00