Does it support NVIDIA TensorRT

[ivoxx]

Does it support NVIDIA TensorRT?

1. inside container cannot read tensorrt engine which generate from same deivce and cuda version ,shows

[TensorRT] WARNING: using an engine plan file across different models of devices is not recommended and is likely to affect performance or enven cause errors

2. inside container some onnx models cannot build tensorrt engine, report segmentation fault

any solution or suggestion?

[xwttzz]

I had the same problem. It is normal to use the whole card, but not once it is fragmented.

[mYmNeo]

The gpu-manager version and log?

[xwttzz]

日志看起来是正常的。 manager的版本是1.1.4 @mYmNeo 方便加个微信号？

[mYmNeo]

Please follow the FAQ, provides the application container log

[ivoxx]

[xwttzz]

this is the container log. @mYmNeo

[mYmNeo]

You need following the FAQ, set environment first, then run your application, the expected log should have /tmp/xxx pattern

[xwttzz]

I have followed the FAQ。

I can't find any useful logs in this directory。Which log in this directory do you want。
@mYmNeo

[mYmNeo]

I have followed the FAQ。

I can't find any useful logs in this directory。Which log in this directory do you want。
@mYmNeo

1. Export LOGGER_LEVEL environment
2. run your application
3. vcuda log will print on the screen

[xwttzz]

https://gist.github.com/xwttzz/1f4b3794a2fb19f430ebea828030d145
The above link shows all logs after VCUDA is enabled。
@mYmNeo

[mYmNeo]

https://gist.github.com/xwttzz/1f4b3794a2fb19f430ebea828030d145
The above link shows all logs after VCUDA is enabled。
@mYmNeo

The error shows you application missing library ImportError: libnvinfer.so.7: cannot open shared object file: No such file or directory, this is not VCUDA library

[xwttzz]

The confusing part is that when I set vcore to 100 it is ok, only when it is fragmented 。 Besides, it has been confirmed that LibnVinfer has been installed in the container.
@mYmNeo

[mYmNeo]

How about re-pull the image thomassong/gpu-manager:1.1.5. We have fixed a recursive problem about vcuda.

[xwttzz]

I updated the latest log in the original address. [https://gist.github.com/xwttzz/1f4b3794a2fb19f430ebea828030d145]
Libnvinfer was a historical log and it has nothing to do with this。
@mYmNeo

[mYmNeo]

https://gist.github.com/xwttzz/1f4b3794a2fb19f430ebea828030d145

I think you should debug the coredump to find where it crash

[austingg]

@xwttzz have u solved the problem ?

[so2bin]

I have the same problem, is anyone have a solution?

[alex337]

I have the same problem, is anyone have a solution?

Hi,have u solved the problem ?

[vicmeng]

tkestack/vcuda-controller#38 (comment)
具体报错