3080Ti could not build cuda engine #264

New Issue

Closed

opened 2021-09-10 09:03:08 +02:00 by lswgh · 4 comments

lswgh commented 2021-09-10 09:03:08 +02:00 (Migrated from github.com)

Copy Link

Copy Source

Hi,I build the demo with cuda10.2, cudnn7.6.5 and TensorRT-7.0.0.11 in nvidia 3080Ti，when i convert the yolov3 weights to rt , the error appear as follow:

so i convert the weights in my 1080Ti ，it work well ,but when i copy the rt weight to 3080Ti, and run ./demo yolo3_fp16.rt ../demo/yolo_test.mp4 y

Hi,I build the demo with cuda10.2, cudnn7.6.5 and TensorRT-7.0.0.11 in nvidia 3080Ti，when i convert the yolov3 weights to rt , the error appear as follow:  so i convert the weights in my 1080Ti ，it work well ,but when i copy the rt weight to 3080Ti, and run ./demo yolo3_fp16.rt ../demo/yolo_test.mp4 y 

perseusdg commented 2021-09-10 09:06:15 +02:00 (Migrated from github.com)

Copy Link

Copy Source

I doubt a 3080ti supports cuda 10.2,you might want to try cuda 11.1 +
https://arnon.dk/matching-sm-architectures-arch-and-gencode-for-various-nvidia-cards/

I doubt a 3080ti supports cuda 10.2,you might want to try cuda 11.1 + https://arnon.dk/matching-sm-architectures-arch-and-gencode-for-various-nvidia-cards/

lswgh commented 2021-09-10 10:11:23 +02:00 (Migrated from github.com)

Copy Link

Copy Source

I doubt a 3080ti supports cuda 10.2,you might want to try cuda 11.1 +
https://arnon.dk/matching-sm-architectures-arch-and-gencode-for-various-nvidia-cards/

thanks for you concern ,
i try to build the demo with tensort7.2 cuda11.2 cudnn8.1 and tensort8.0 cuda11.2 cudnn8.1 ,but failed ,

I doubt that TKDNN is not support cuda11.1 + .

> I doubt a 3080ti supports cuda 10.2,you might want to try cuda 11.1 + > https://arnon.dk/matching-sm-architectures-arch-and-gencode-for-various-nvidia-cards/ thanks for you concern , i try to build the demo with tensort7.2 cuda11.2 cudnn8.1 and tensort8.0 cuda11.2 cudnn8.1 ,but failed ,  I doubt that TKDNN is not support cuda11.1 + .

perseusdg commented 2021-09-10 10:15:45 +02:00 (Migrated from github.com)

Copy Link

Copy Source

tkdnn doesnt support tensorrt 8+,i have used tkDNN tensorrt7.2+cuda11.1+ cudnn8.1.1 (if you want to use tensorrt 7.2 with cuda 11.2 you still need cuda 11.1 because nvrtc from cuda 11.1 is still a reuqirement of tensorrt 7.2) https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-7.html#rel_7-2-3

tkdnn doesnt support tensorrt 8+,i have used tkDNN tensorrt7.2+cuda11.1+ cudnn8.1.1 (if you want to use tensorrt 7.2 with cuda 11.2 you still need cuda 11.1 because nvrtc from cuda 11.1 is still a reuqirement of tensorrt 7.2) https://docs.nvidia.com/deeplearning/tensorrt/release-notes/tensorrt-7.html#rel_7-2-3

👍 1

lswgh commented 2021-09-10 11:14:44 +02:00 (Migrated from github.com)

Copy Link

Copy Source

.2+
Thanks , when i build with tensorrt7.2 cuda11.1 cudnn8.1 , it works , but compare to the 1080Ti(900M for FP32) , the memory run on 3080Ti used more (about 2.9G for FP32 and 2.5G for FP16),

> .2+ Thanks , when i build with tensorrt7.2 cuda11.1 cudnn8.1 , it works , but compare to the 1080Ti(900M for FP32) , the memory run on 3080Ti used more (about 2.9G for FP32 and 2.5G for FP16),

This repo is archived. You cannot comment on issues.

No Branch/Tag Specified

Branches Tags

master

dev_rtls

mbzirc

tensorrt7

gpu-prepocess

resize

yolo4tiny

cudnn-8.0.1

class

cudnn5

cudnn2

v0.7

v0.6

v0.5

v0.4

testData

Labels

Clear labels

bug

duplicate

enhancement

explanation

help wanted

invalid

question

wontfix

No Label

Milestone

No items

No Milestone

Assignees

Clear assignees

eeeck (Erick)

No Assignees

1 Participants

Due Date

No due date set.

Dependencies

No dependencies set.

Reference: mmr/tkDNN#264