Skip to content

Actions: NVIDIA/TensorRT

Actions

All workflows

Actions

Loading...

Showing runs from all workflows
4,660 workflow runs
4,660 workflow runs
Event

Filter by event
Status

Filter by status
Branch
Actor

Filter by actor
example of sd tensorrt model and Lora/ControlNet model fusion by refit? Blossom-CI #4655: Issue comment #3032 (comment) created by bigmover
May 29, 2024 09:45 4s
May 29, 2024 09:45 4s
Blossom-CI Blossom-CI #4654: created by biubiu3721
May 29, 2024 09:14 3s
May 29, 2024 09:14 3s
Blossom-CI Blossom-CI #4653: created by biubiu3721
May 29, 2024 09:13 5s
May 29, 2024 09:13 5s
Why can't we set the precision of all layers to fp16 or fp32? Blossom-CI #4652: Issue comment #3177 (comment) created by biubiu3721
May 29, 2024 09:12 5s
May 29, 2024 09:12 5s
Reuse engine for multiple consequent runs Blossom-CI #4651: Issue comment #3868 (comment) created by KyriaAnnwyn
May 29, 2024 07:02 4s
May 29, 2024 07:02 4s
Result of FP16 TensorRT model is NOT correct Blossom-CI #4650: Issue comment #3827 (comment) created by AndreWanga
May 29, 2024 05:21 4s
May 29, 2024 05:21 4s
deserialize engine fail on tensorrt 7.2.2.3 Blossom-CI #4649: Issue comment #3911 (comment) created by Luwill6
May 29, 2024 04:39 3s
May 29, 2024 04:39 3s
slower inference speed of TensorRT 10.0 on GPU Tesla T4 Blossom-CI #4648: Issue comment #3896 (comment) created by zerollzeng
May 29, 2024 01:47 4s
May 29, 2024 01:47 4s
Is there any gpu memory difference when using different context in TensorRT 8.4.0.6 ? Blossom-CI #4647: Issue comment #3907 (comment) created by Jsy0220
May 29, 2024 01:32 5s
May 29, 2024 01:32 5s
New Plugin YoloNMS Blossom-CI #4646: Issue comment #3859 (comment) created by levipereira
May 28, 2024 20:42 3s
May 28, 2024 20:42 3s
Virtually no detections after detectron2->onnx->onnx->TensorRT conversion of Mask RCNN. Blossom-CI #4645: Issue comment #3792 (comment) created by azhurkevich
May 28, 2024 17:00 5s
May 28, 2024 17:00 5s
Accuracy failure of TensorRT 8.6.3 when running trtexec built engine on GPU RTX4090 Blossom-CI #4644: Issue comment #3893 (comment) created by brb-nv
May 28, 2024 16:26 5s
May 28, 2024 16:26 5s
[Question] Is IOutputAllocator::reallocateOutput guaranteed to be called before context->enqueueV3 returns? Blossom-CI #4643: Issue comment #3875 (comment) created by mirzadeh
May 28, 2024 15:07 5s
May 28, 2024 15:07 5s
pytorch-quantization example is incompatible with latest torchvision version Blossom-CI #4642: Issue comment #3495 (comment) created by spinzello
May 28, 2024 12:52 35s
May 28, 2024 12:52 35s
Is there any gpu memory difference when using different context in TensorRT 8.4.0.6 ? Blossom-CI #4641: Issue comment #3907 (comment) created by lix19937
May 28, 2024 11:43 4s
May 28, 2024 11:43 4s
TensorRT can not support custom op grid_sampler Blossom-CI #4640: Issue comment #2612 (comment) created by zmtttt
May 28, 2024 10:10 4s
May 28, 2024 10:10 4s
[shuffleBuilder.cpp::writeGlob::154] Error Code 2: Internal Error (Assertion outputScalesLen >= quantizations.outputs[0].scale.count() failed. ) Blossom-CI #4639: Issue comment #3904 (comment) created by lix19937
May 28, 2024 09:34 4s
May 28, 2024 09:34 4s
GridSample Using trtexec to convert gridsample arithmetic reports an error Blossom-CI #4638: Issue comment #3207 (comment) created by tianlinzx
May 28, 2024 09:29 4s
May 28, 2024 09:29 4s
GridSample Using trtexec to convert gridsample arithmetic reports an error Blossom-CI #4637: Issue comment #3207 (comment) created by zmtttt
May 28, 2024 09:00 4s
May 28, 2024 09:00 4s
GridSample Using trtexec to convert gridsample arithmetic reports an error Blossom-CI #4636: Issue comment #3207 (comment) created by zmtttt
May 28, 2024 08:52 4s
May 28, 2024 08:52 4s
New Plugin YoloNMS Blossom-CI #4635: Issue comment #3859 (comment) created by samurdhikaru
May 28, 2024 08:24 5s
May 28, 2024 08:24 5s
Result of FP16 TensorRT model is NOT correct Blossom-CI #4634: Issue comment #3827 (comment) created by AndreWanga
May 28, 2024 07:29 5s
May 28, 2024 07:29 5s
[shuffleBuilder.cpp::writeGlob::154] Error Code 2: Internal Error (Assertion outputScalesLen >= quantizations.outputs[0].scale.count() failed. ) Blossom-CI #4633: Issue comment #3904 (comment) created by lix19937
May 28, 2024 07:09 4s
May 28, 2024 07:09 4s
trtexec: onnx to tensorRT convertion fails Blossom-CI #4632: Issue comment #3894 (comment) created by brb-nv
May 28, 2024 05:57 3s
May 28, 2024 05:57 3s
Improving int8 quantization results. Blossom-CI #4631: Issue comment #3865 (comment) created by brb-nv
May 28, 2024 05:43 4s
May 28, 2024 05:43 4s