Skip to content

Actions: NVIDIA/TensorRT

Actions

All workflows

Actions

Loading...
Loading

Showing runs from all workflows
4,954 workflow runs
4,954 workflow runs

Filter by Event

Filter by Status

Filter by Branch

Filter by Actor

Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::enqueueV3::2666, condition: mContext.profileObliviousBindings.at(profileObliviousIndex) || getPtrOrNull(mOutputAllocators, profileObliviousIndex)) Blossom-CI #6558: Issue comment #4224 (comment) created by kevinch-nv
December 13, 2024 20:24 4s
December 13, 2024 20:24 4s
INT8EntropyCalibrator2 implicit quantization superseded by explicit quantization Blossom-CI #6557: Issue comment #4095 (comment) created by moraxu
December 13, 2024 19:52 5s
December 13, 2024 19:52 5s
Polygraphy GPU memory leak when processing a large enough number of images Blossom-CI #6556: Issue comment #3791 (comment) created by ludekcizinsky
December 13, 2024 12:00 5s
December 13, 2024 12:00 5s
incompatible types Int64 and Int32 Blossom-CI #6555: Issue comment #4268 (comment) created by antithing
December 13, 2024 07:18 4s
December 13, 2024 07:18 4s
incompatible types Int64 and Int32 Blossom-CI #6554: Issue comment #4268 (comment) created by LeoZDong
December 13, 2024 00:14 5s
December 13, 2024 00:14 5s
[Feature request] allow uint8 output without an ICastLayer before Blossom-CI #6553: Issue comment #4282 (comment) created by QMassoz
December 12, 2024 14:47 5s
December 12, 2024 14:47 5s
[Feature request] allow uint8 output without an ICastLayer before Blossom-CI #6552: Issue comment #4278 (comment) created by QMassoz
December 12, 2024 14:43 4s
December 12, 2024 14:43 4s
Blossom-CI Blossom-CI #6551: created by QMassoz
December 12, 2024 14:43 5s
December 12, 2024 14:43 5s
Error Code 6: Internal Error (Loop API is not supported on this configuration. This may be because the requested platform does not support loops, or because TensorRT has been statically linked.) Blossom-CI #6550: Issue comment #1737 (comment) created by linus-gates
December 12, 2024 11:45 5s
December 12, 2024 11:45 5s
TopK 3840 limitation and future plans for this operator Blossom-CI #6549: Issue comment #4244 (comment) created by amadeuszsz
December 12, 2024 11:26 5s
December 12, 2024 11:26 5s
Polygraphy GPU memory leak when processing a large enough number of images Blossom-CI #6548: Issue comment #3791 (comment) created by michaeldeyzel
December 11, 2024 09:17 6s
December 11, 2024 09:17 6s
How to make 4bit pytorch_quantization model export to .engine model? Blossom-CI #6547: Issue comment #4262 (comment) created by StarryAzure
December 11, 2024 07:20 6s
December 11, 2024 07:20 6s
converting to TensorRT barely increases performance Blossom-CI #6546: Issue comment #3646 (comment) created by watertianyi
December 11, 2024 07:14 4s
December 11, 2024 07:14 4s
TensorRT8.6.1.6 Inference cost too much time Blossom-CI #6545: Issue comment #3993 (comment) created by watertianyi
December 11, 2024 06:16 5s
December 11, 2024 06:16 5s
TensorRT8.6.1.6 Inference cost too much time Blossom-CI #6544: Issue comment #3993 (comment) created by xxHn-pro
December 11, 2024 04:00 4s
December 11, 2024 04:00 4s
INT8 Quantization of dinov2 TensorRT Model is Not Faster than FP16 Quantization Blossom-CI #6543: Issue comment #4273 (comment) created by lix19937
December 11, 2024 00:44 5s
December 11, 2024 00:44 5s
Is there a plan to support more recent PTQ methods for INT8 ViT? Blossom-CI #6542: Issue comment #4276 (comment) created by lix19937
December 11, 2024 00:41 5s
December 11, 2024 00:41 5s
Disable/Enable graph level optimizations Blossom-CI #6541: Issue comment #4275 (comment) created by lix19937
December 11, 2024 00:40 4s
December 11, 2024 00:40 4s
Accuracy loss of TensorRT 8.6 when running INT8 Quantized Resnet18 on GPU A4000 Blossom-CI #6540: Issue comment #4079 (comment) created by YixuanSeanZhou
December 10, 2024 21:39 5s
December 10, 2024 21:39 5s
Error Code 3: API Usage Error (Parameter check failed at: runtime/api/executionContext.cpp::enqueueV3::2666, condition: mContext.profileObliviousBindings.at(profileObliviousIndex) || getPtrOrNull(mOutputAllocators, profileObliviousIndex)) Blossom-CI #6539: Issue comment #4224 (comment) created by fgias
December 10, 2024 11:01 5s
December 10, 2024 11:01 5s
Plugin inference and loading from onnx Blossom-CI #6538: Issue comment #4266 (comment) created by idantene
December 10, 2024 09:19 5s
December 10, 2024 09:19 5s
TensorRT8.6.1.6 Inference cost too much time Blossom-CI #6537: Issue comment #3993 (comment) created by watertianyi
December 10, 2024 08:24 5s
December 10, 2024 08:24 5s
Different versions of TensorRT get different model inference results on GroundingDino model Blossom-CI #6536: Issue comment #4209 (comment) created by demuxin
December 10, 2024 02:50 5s
December 10, 2024 02:50 5s
Different versions of TensorRT get different model inference results on GroundingDino model Blossom-CI #6535: Issue comment #4209 (comment) created by demuxin
December 10, 2024 01:38 5s
December 10, 2024 01:38 5s
Plugin inference and loading from onnx Blossom-CI #6534: Issue comment #4266 (comment) created by venkywonka
December 10, 2024 01:34 6s
December 10, 2024 01:34 6s