Issues
- 8
- 1
Can it be uploaded/released to pypi.org?
#36 opened by albertodallolio - 1
Encountered known unsupported method torch.nn.functional.has_torch_function_variadic
#35 opened by zhouchang413057247 - 3
Error Code 9: Internal Error ((Unnamed Layer* 3886) [ElementWise]: broadcast dimensions must be conformable )
#21 opened by Tailwhip - 2
- 2
- 2
install error
#5 opened by zkloveai - 2
Hi, how to solve it with list output?
#13 opened by lucasjinreal - 4
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)
#30 opened by LeoRainly - 0
Consumes 25% of RAM
#28 opened by sathisha-beltech - 2
Error number of channels in input tensor to a convolution layer must not be dynamic
#27 opened by Kracozebr - 3
- 1
- 4
Why official torch2trt doesn't invoke any plugin, but this invoke too many plugins even with simple model
#7 opened by lucasjinreal - 0
TRT8 AttributeError: 'tensorrt.tensorrt.Builder' object has no attribute 'int8_calibrator'
#22 opened by v-qjqs - 16
No warnings, but [TensorRT] ERROR: INVALID_ARGUMENT: Cannot find binding of given name: input_0
#19 opened by iAlexKai - 2
- 4
- 5
RuntimeError: NVRTC error when convert model
#16 opened by HHZ94 - 13
converted bart model is slower than the original one during inference time
#14 opened by zangyuchen2008 - 2
- 1
set_calibration_profile not exist
#12 opened by Chen-cyw - 5
load libtorch2trt_dynamic.so error
#11 opened by Chen-cyw - 2
Max_error in Interpolate Plugin
#10 opened by zhujiandream - 2
topk issue
#8 opened by niaoyu - 2
- 4
is this library supposed to be compatible with original torch2trt library?
#6 opened by gengshenghong - 7
c++ inference
#4 opened by lucasjinreal - 5
- 2
/libamirstan_plugin.so
#1 opened by semchan