q.yao torch2trt_dynamic Issues

grimoire/torch2trt_dynamic Issues

Error Code 9: Internal Error ((Unnamed Layer* 3886) [ElementWise]: broadcast dimensions must be conformable )
Updated a year ago3
getPluginCreator could not find plugin RepeatDimsPluginDynamic version 1
Updated 2 years ago2
No module named 'torch2trt_dynamic.converters.identity'
Closed 2 years ago2
install error
Updated 2 years ago2
Hi, how to solve it with list output?
Updated 2 years ago2
WARNING: Myelin graph with multiple dynamic values may have poor performance if they differ. Dynamic values are: (+ (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (+ (# 3 (SHAPE input_0)) -1) 2) 2) 2) 2) 2) 1) (+ (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (FLOOR_DIV (+ (# 2 (SHAPE input_0)) -1) 2) 2) 2) 2) 2) 1)
Updated 2 years ago4
Consumes 25% of RAM
Updated 2 years ago
Error number of channels in input tensor to a convolution layer must not be dynamic
Updated 2 years ago2
Consider adding support for DLA (Deep learning accelerator) modules
Updated 2 years ago3
how to add a converter for custom operateion written by c++
Updated 3 years ago1
Why official torch2trt doesn't invoke any plugin, but this invoke too many plugins even with simple model
Updated 3 years ago4
TRT8 AttributeError: 'tensorrt.tensorrt.Builder' object has no attribute 'int8_calibrator'
Closed 3 years ago
No warnings, but [TensorRT] ERROR: INVALID_ARGUMENT: Cannot find binding of given name: input_0
Closed 3 years ago16
Does int8 calibration DatasetCalibrator buffer support multiple inputs?
Closed 3 years ago2
Warning: Encountered known unsupported method torch.Tensor.__format__
Closed 3 years ago4
RuntimeError: NVRTC error when convert model
Updated 3 years ago5
converted bart model is slower than the original one during inference time
Updated 3 years ago13
Error, while converting fastrcnn torchvision model
Updated 3 years ago2
set_calibration_profile not exist
Updated 3 years ago1
load libtorch2trt_dynamic.so error
Updated 3 years ago5
Max_error in Interpolate Plugin
Updated 3 years ago2
topk issue
Closed 4 years ago2
Is it possible to disable dynamic_shape feature?
Closed 4 years ago2
is this library supposed to be compatible with original torch2trt library?
Closed 4 years ago4
c++ inference
Updated 4 years ago7
Any idea on how to support ConvTranspose2d？
Closed 4 years ago5
/libamirstan_plugin.so
Updated 4 years ago2

grimoire / torch2trt_dynamic

grimoire/torch2trt_dynamic Issues

Error Code 9: Internal Error ((Unnamed Layer* 3886) [ElementWise]: broadcast dimensions must be conformable )

getPluginCreator could not find plugin RepeatDimsPluginDynamic version 1

No module named 'torch2trt_dynamic.converters.identity'

install error

Hi, how to solve it with list output?

Consumes 25% of RAM

Error number of channels in input tensor to a convolution layer must not be dynamic

Consider adding support for DLA (Deep learning accelerator) modules

how to add a converter for custom operateion written by c++

Why official torch2trt doesn't invoke any plugin, but this invoke too many plugins even with simple model

TRT8 AttributeError: 'tensorrt.tensorrt.Builder' object has no attribute 'int8_calibrator'

No warnings, but [TensorRT] ERROR: INVALID_ARGUMENT: Cannot find binding of given name: input_0

Does int8 calibration DatasetCalibrator buffer support multiple inputs?

Warning: Encountered known unsupported method torch.Tensor.format

RuntimeError: NVRTC error when convert model

converted bart model is slower than the original one during inference time

Error, while converting fastrcnn torchvision model

set_calibration_profile not exist

load libtorch2trt_dynamic.so error

Max_error in Interpolate Plugin

topk issue

Is it possible to disable dynamic_shape feature?

is this library supposed to be compatible with original torch2trt library?

c++ inference

Any idea on how to support ConvTranspose2d？

/libamirstan_plugin.so