kkudrynski
|
5d36b4fd2f
|
Fixing hyperlinks
|
2020-09-08 16:10:32 +02:00 |
|
|
nv-kkudrynski
|
323005c443
|
Merge pull request #676 from NVIDIA/gh/release
[DLRM/PyT] Triton updates
|
2020-09-08 12:10:28 +02:00 |
|
|
kkudrynski
|
21fcdd6fcf
|
[DLRM/PyT] Triton updates
|
2020-09-07 16:19:47 +02:00 |
|
Sharath T S
|
8588e9834c
|
[BERT/PyT] specify GPU for triton (#666)
|
2020-09-01 22:07:36 -07:00 |
|
|
Sharath T S
|
5cc03caa15
|
[BERT/PyT] Update pretrained checkpoint links (#660)
* Update pretrained checkpoint links
* update link
|
2020-08-21 13:34:05 -07:00 |
|
|
nv-kkudrynski
|
0e6cfbd0a1
|
Merge pull request #659 from hXl3s/RN50/readme-update
[ConvNets/TF] Document synthetic dataset options
|
2020-08-20 16:45:53 +02:00 |
|
Łukasz Pierścieniewski
|
8bd6dd14d3
|
Document synthetic dataset options
|
2020-08-20 16:21:50 +02:00 |
|
|
Sharath T S
|
446c878878
|
[ELECTRA/TF2] Update inference latency (#657)
* Update inference latency
* Fix inference perf numbers
* Fix latency computation
|
2020-08-19 20:43:44 -07:00 |
|
|
nv-kkudrynski
|
bbbc823072
|
Merge pull request #655 from NVIDIA/gh/release
[DLRM/PyT] Readme fixes
|
2020-08-18 15:06:23 +02:00 |
|
|
kkudrynski
|
0d15a95c8f
|
[DLRM/PyT] Readme fixes
|
2020-08-18 15:04:47 +02:00 |
|
|
nv-kkudrynski
|
d875531dd6
|
Merge pull request #654 from NVIDIA/dlrm_update
[DLRM/PyT] Update
|
2020-08-17 13:22:23 +02:00 |
|
|
kkudrynski
|
3745b49898
|
[DLRM/PyT] Update
|
2020-08-17 11:14:46 +02:00 |
|
|
nv-kkudrynski
|
ff7e38bf87
|
Merge pull request #650 from NVIDIA/bert_pyt_mrpc
[BERT/PyT] MRPC and SST-2 support
|
2020-08-14 16:51:27 +02:00 |
|
|
kkudrynski
|
88864b9291
|
[BERT/PyT] MRPC and SST-2 support
|
2020-08-14 16:43:11 +02:00 |
|
Swetha Mandava
|
7c0afee460
|
Merge pull request #648 from swethmandava/master
Bert TF download tfrecords with correct name
|
2020-08-13 12:55:58 -07:00 |
|
Swetha Mandava
|
9d4c9f3eb0
|
tfrecords with correct name
|
2020-08-13 12:52:46 -07:00 |
|
Pablo Ribalta Lorenzo
|
fb40734b31
|
Remove autobench scripts (#647)
Signed-off-by: Pablo Ribalta <pribalta@nvidia.com>
|
2020-08-12 11:48:46 -07:00 |
|
|
nv-kkudrynski
|
41a0891313
|
Merge pull request #645 from NVIDIA/sharathts-patch-4
Keep wikiextractor version fixed
|
2020-08-11 18:49:52 +02:00 |
|
|
Swetha Mandava
|
c8bbdb5798
|
Merge pull request #644 from swethmandava/master
Bert tf update (triton v2, fixes)
|
2020-08-11 08:29:39 -07:00 |
|
|
Swetha Mandava
|
1069a7358c
|
converge to pyt
|
2020-08-10 13:15:39 -07:00 |
|
|
Sharath T S
|
e8f87acdb1
|
Keep wikiextractor version fixed
|
2020-08-10 11:46:17 -07:00 |
|
|
Swetha Mandava
|
efd6384176
|
pointing to wikiextractor commit
|
2020-08-10 11:27:47 -07:00 |
|
|
Swetha Mandava
|
b82c372047
|
triton v2 api, download mrpc fix, update for mpi 4.2
|
2020-08-10 11:09:40 -07:00 |
|
|
Swetha Mandava
|
769843e51a
|
Merge pull request #11 from NVIDIA/master
Update Aug 10 2020
|
2020-08-10 11:04:43 -07:00 |
|
|
nv-kkudrynski
|
36ad5fe657
|
Update .gitmodules
|
2020-08-06 15:01:22 +02:00 |
|
BO-YANG HSUEH
|
1aa6813450
|
[FT] 1. Fix the bug of TensorRT plugin of FasterTransformer encoder. (#640)
* [FT] 1. Fix the bug of TensorRT plugin of FasterTransformer encoder.
|
2020-08-06 20:15:49 +08:00 |
|
|
nv-kkudrynski
|
280e75c63e
|
Merge pull request #636 from NVIDIA/gh/release
[VAE/TF] Updating for Ampere
|
2020-08-05 20:55:02 +02:00 |
|
|
kkudrynski
|
22f354e8ff
|
[VAE/TF] Updating for Ampere
|
2020-08-05 20:52:38 +02:00 |
|
|
nv-kkudrynski
|
386dd8ebf6
|
Merge pull request #630 from NVIDIA/gh/release
Updating GNMT/PyT/TF for Ampere, fixes in WnD/TF and Jasper/PyT
|
2020-08-05 17:01:16 +02:00 |
|
|
kkudrynski
|
2356b898f5
|
[WideAndDeep/TF] scripts fix
|
2020-08-05 16:55:31 +02:00 |
|
|
kkudrynski
|
557f4d01ea
|
[Jasper/PyT] Triton update
|
2020-08-05 16:44:50 +02:00 |
|
|
kkudrynski
|
9fa75813e6
|
Merge branch 'gh/master' into gh/release
|
2020-08-05 16:38:18 +02:00 |
|
|
Sharath T S
|
1f9226283e
|
[BERT/PyT] link gitlab -> DLE (#634)
|
2020-08-03 22:02:55 -07:00 |
|
|
Pablo Ribalta Lorenzo
|
409f03c004
|
Merge pull request #631 from NVIDIA/unetmed-perf-fix
Update README.md
|
2020-08-03 09:17:08 +02:00 |
|
Dabi Ahn
|
d8cc4a99ce
|
remove pretrained aligns and update readme accordingly.
|
2020-08-03 12:39:30 +08:00 |
|
Michał Marcinkiewicz
|
adddf66b9c
|
Update README.md
|
2020-08-02 19:35:09 +02:00 |
|
|
kkudrynski
|
360d1f4175
|
[GNMT/TF] Updating for Ampere
|
2020-08-01 16:04:02 +02:00 |
|
|
kkudrynski
|
5d2914e3ff
|
[GNMT/PyT] Updating for Ampere]
|
2020-08-01 15:47:34 +02:00 |
|
|
Swetha Mandava
|
21a77af396
|
Merge pull request #617 from trentlo/async_io_for_squad
Enable async_io for squad.
|
2020-07-31 10:32:50 -07:00 |
|
PrzemekS
|
a2a5e00878
|
Merge pull request #629 from andabi/master
Add FastSpeech in CUDA-Optimized
|
2020-07-31 17:44:41 +02:00 |
|
|
Dabi Ahn
|
e0fcb62e83
|
Add FastSpeech in CUDA-Optimized
|
2020-07-31 14:59:15 +08:00 |
|
|
Sharath T S
|
5a87078d25
|
[Electra/TF2] Fix container image and num_gpu arg (#628)
* Fix container image
* fix num_gpu arg
|
2020-07-30 14:48:34 -07:00 |
|
|
PrzemekS
|
a275790df4
|
Merge pull request #623 from alvarognvidia/master
Update README.md
|
2020-07-30 17:55:59 +02:00 |
|
Alvaro Garcia
|
63a2a2e431
|
Update README.md
|
2020-07-27 07:41:03 -07:00 |
|
|
PrzemekS
|
cd7d870749
|
Merge pull request #619 from NVIDIA/pribalta/maskrcnn_checkpoint_update
Update checkpoint MaskRCNN
|
2020-07-23 15:07:38 +02:00 |
|
Pablo Ribalta
|
f4625a2935
|
Update checkpoint MaskRCNN
Signed-off-by: Pablo Ribalta <pribalta@nvidia.com>
|
2020-07-23 15:00:13 +02:00 |
|
Trent Lo
|
388f1acbc0
|
Insert needed space as seperator.
|
2020-07-22 19:08:55 -07:00 |
|
|
Trent Lo
|
f3f1311e43
|
Enable async_io for squad.
|
2020-07-22 17:10:51 -07:00 |
|
Amr Ragab
|
9ba22d1f29
|
[MaskRCNN/TF] Update extract_RN50_weights.py (#597)
* Update extract_RN50_weights.py
removing contrib - not compatible with TF2.0
* Update extract_RN50_weights.py
adding compat with tf1 and tf2
|
2020-07-22 17:01:27 -07:00 |
|
|
Sharath T S
|
0ef5568a9d
|
[BERT/PyT] default train:test 9:1 (#616)
|
2020-07-22 14:07:50 -07:00 |
|