search

laugh12321 / TensorRT-YOLO

🚀 你的YOLO部署神器。TensorRT Plugin、CUDA Kernel、CUDA Graphs三管齐下，享受闪电般的推理速度。| Your YOLO Deployment Powerhouse. With the synergy of TensorRT Plugins, CUDA Kernels, and CUDA Graphs, experience lightning-fast inference speeds.
https://github.com/laugh12321/TensorRT-YOLO
GNU General Public License v3.0
540 stars 67 forks source link

[CUDA ERROR]: Too many resources requested for launch #11

Closed liautumn closed 5 months ago

liautumn commented 5 months ago

image 代码也没动，运行就报这个问题

laugh12321 commented 5 months ago

你看看你用的显卡最大支持每个块有多少个线程，代码里是3232个，你改成1616试一下。

// dim3 blockSize(32, 32);
dim3 blockSize(16, 16);
liautumn commented 5 months ago

ok, 感谢