Przemek Strzelczyk
|
15ba45666d
|
[WideAndDeep] Improved Spark preprocessing scripts performance
|
2020-05-18 01:11:27 +02:00 |
|
Sharath T S
|
9df464f277
|
[BERT/PyT] stop and resume, single gpu and timing fixes. (#509)
* stop and resume, single gpu and timing fixes.
* Update utils.py
* accumulation features check
|
2020-05-17 12:46:53 -07:00 |
|
Sharath T S
|
3aae0204c3
|
1. stop and resume
|
2020-05-16 22:47:53 -07:00 |
|
GrzegorzKarchNV
|
78aacb4797
|
Merge pull request #504 from GrzegorzKarchNV/trtis-fixes
[Tacotron2] Triton fixes
|
2020-05-14 22:29:30 +02:00 |
|
gkarch
|
bf2b7a0767
|
fixed trtis dockerfile
|
2020-05-14 22:24:54 +02:00 |
|
gkarch
|
8d8337196f
|
fixed trtis
|
2020-05-14 19:58:45 +02:00 |
|
BO-YANG HSUEH
|
92ac3236ea
|
Merge pull request #501 from byshiue/master
[FasterTransformer] Fix bug of trt sample.
|
2020-05-13 17:40:59 +08:00 |
|
bhsueh
|
13e601c6e4
|
1. Fix the bugs of trt sample codes
|
2020-05-13 09:38:33 +00:00 |
|
GrzegorzKarchNV
|
6fa33f63c6
|
Merge pull request #500 from GrzegorzKarchNV/master
[Tacotron2] fixed load_and_setup_model in ONNX exports
|
2020-05-13 11:27:45 +02:00 |
|
gkarch
|
86dc81241c
|
[Tacotron2] fixed load_and_setup_model in ONNX exports
|
2020-05-13 11:24:39 +02:00 |
|
GrzegorzKarchNV
|
42ba4eab16
|
Merge pull request #499 from GrzegorzKarchNV/master
[Tacotron2] fixed get_model in train.py
|
2020-05-13 11:12:11 +02:00 |
|
gkarch
|
1272f6fafa
|
[Tacotron2] fixed get_model in train.py
|
2020-05-13 11:08:15 +02:00 |
|
jconwayNV
|
072f2cbb07
|
Updated some TRTIS references to Triton
|
2020-05-11 23:18:50 -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 |
|
PrzemekS
|
b88db70dc1
|
Merge pull request #448 from NVIDIA/unet_industrial_fixes
Update UNet industrial
|
2020-05-07 11:09:46 +02:00 |
|
PrzemekS
|
af32ac2a23
|
Merge pull request #456 from NVIDIA/sharathts-patch-1
Fix to load Google's checkpoint
|
2020-05-07 11:09:20 +02:00 |
|
PrzemekS
|
5175cc77eb
|
Merge pull request #469 from swethmandava/master
Adding DLLogger
|
2020-05-07 11:08:17 +02:00 |
|
PrzemekS
|
d218a72914
|
Merge pull request #470 from NVIDIA/unetmed_tf2-loss_fix
Replace softmax_cross_entropy_with_logits with binary_crossentropy
|
2020-05-07 11:07:36 +02:00 |
|
GrzegorzKarchNV
|
2340f70d55
|
Merge pull request #486 from maggiezha/master
add Intel optimization for PyTorch
|
2020-05-07 08:35:19 +02:00 |
|
maggiezha
|
387f700c4c
|
add Intel Optimization for PyTorch
Intel's optimization for PyTorch on CPU are added, you need to set "export OMP_NUM_THREADS=num physical cores" based on your CPU's core number
|
2020-05-07 15:57:07 +10:00 |
|
maggiezha
|
150f877e19
|
adding CPU optimization
export OMP_NUM_THREADS=num physical cores
export KMP_BLOCKTIME=0
export KMP_AFFINITY=granularity=fine,compact,1,0
https://software.intel.com/content/www/us/en/develop/articles/maximize-tensorflow-performance-on-cpu-considerations-and-recommendations-for-inference.html
|
2020-05-07 15:51:45 +10:00 |
|
GrzegorzKarchNV
|
67a7d9c4eb
|
Merge pull request #482 from maggiezha/cpu-run
Cpu run
|
2020-05-06 21:27:26 +02:00 |
|
GrzegorzKarchNV
|
c26a383288
|
Merge pull request #483 from GrzegorzKarchNV/trt_const_batch
constant batch in TensorRT engine build
|
2020-05-06 15:26:37 +02:00 |
|
maggiezha
|
acf833f7e4
|
adding support for --cpu-run
|
2020-05-06 21:57:05 +10:00 |
|
maggiezha
|
3a6b667118
|
adding support for --cpu-run
|
2020-05-06 21:52:49 +10:00 |
|
maggiezha
|
342c4710fc
|
adding support for --cpu-run
|
2020-05-06 21:48:43 +10:00 |
|
maggiezha
|
0e986cc1f0
|
adding support for --cpu-run
|
2020-05-06 21:46:45 +10:00 |
|
maggiezha
|
ca43a1b1e5
|
adding support for --cpu-run
|
2020-05-06 21:42:43 +10:00 |
|
gkarch
|
d0d4df70a1
|
constant batch in TensorRT engine build
|
2020-05-06 13:01:08 +02:00 |
|
maggiezha
|
a4ce69a5a7
|
add support for --cpu-run
|
2020-05-06 20:58:45 +10:00 |
|
maggiezha
|
9268095bb1
|
add support for --cpu-run
|
2020-05-06 20:57:10 +10:00 |
|
maggiezha
|
3a11f10bfe
|
add support for --cpu-run
|
2020-05-06 20:50:59 +10:00 |
|
Swetha Mandava
|
b7903f0f62
|
Inference throughput computation removing outliers, eval when eval script is given only
|
2020-04-29 14:17:22 -07:00 |
|
BO-YANG HSUEH
|
bee3ddfa0e
|
[FasterTransformer] Fix the bug of Readme.
|
2020-04-29 16:44:22 +08:00 |
|
bhsueh
|
5ee9b2ec03
|
1. [FasterTransformer] Fix the bug of encoder trt plugin.
|
2020-04-29 08:42:43 +00:00 |
|
GrzegorzKarchNV
|
90ce2a9923
|
Merge pull request #471 from GrzegorzKarchNV/trt-infer-fix
fixed trt inference
|
2020-04-27 16:07:24 +02:00 |
|
gkarch
|
b0ab215441
|
fixed trt inference
|
2020-04-27 16:05:33 +02:00 |
|
Michał Marcinkiewicz
|
57b8a6ac3a
|
Update losses.py
Replace softmax_cross_entropy_with_logits with binary_crossentropy
|
2020-04-26 10:24:08 +02:00 |
|
Swetha Mandava
|
c94b73f9ea
|
Adding DLLogger and specificying v1.1 in the readme results for clarity
|
2020-04-24 14:01:53 -07:00 |
|
Swetha Mandava
|
eb8e823c39
|
Merge pull request #7 from NVIDIA/master
Pull from remote
|
2020-04-24 13:50:28 -07:00 |
|
Rajeev Rao
|
33112129c5
|
Fix docker build script
|
2020-04-23 15:40:50 -07:00 |
|
Sharath T S
|
4733603577
|
[BERT/PyT] Fix squad inference corner case (#462)
|
2020-04-20 21:02:18 -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 |
|