Panic with 3090

[teamhzipfs]

I've got the following error after running Bladebit_cude 3.1.0. My system config is 995G RAM and dual RTX 3090 cards with CUDA 12.2 (latest). Really don't see what I've done wrong so if you could please shed some light:

[Bladebit CUDA Plotter]
Host RAM : 995 GiB
Plot checks : disabled

Selected cuda device 0 : NVIDIA GeForce RTX 3090
CUDA Compute Capability : 8.6
SM count : 82
Max blocks per SM : 16
Max threads per SM : 1536
Async Engine Count : 2
L2 cache size : 6.00 MB
L2 persist cache max size : 4.50 MB
Stack Size : 1.00 KB
Memory:
Total : 23.69 GB
Free : 23.44 GB

Allocating buffers (this may take a few seconds)...
Kernel RAM required : 88029694652 bytes ( 83951.66 MiB or 81.98 GiB )
Intermediate RAM required : 73728 bytes ( 0.07 MiB or 0.00 GiB )
Host RAM required : 169080782848 bytes ( 161248.00 MiB or 157.47 GiB )
Total Host RAM required : 257110477500 bytes ( 245199.66 MiB or 239.45 GiB )
GPU RAM required : 6163857408 bytes ( 5878.31 MiB or 5.74 GiB )
Allocating buffers...
Done.

Generating plot 1 / 1: 7e4fa0700f04208074728a7968a37a2fb531e83a744a80186f0969119420d069
Plot temporary file: /mnt/sxxxxxxxxxxxxxxx
7e4fa0700f04208074728a7968a37a2fb531e83a744a80186f0969119420d069.plot.tmp

Generating F1
Finished F1 in 1.64 seconds.
CUDA error: 700 (0x2bc) cudaErrorIllegalAddress : an illegal memory access was encountered

*** Panic!!! *** Fatal Error:
CUDA error cudaErrorIllegalAddress : an illegal memory access was encountered.
./bladebit_cuda(_ZN7SysHost14DumpStackTraceEv+0x5b)[0x560534eb630b]
./bladebit_cuda(_Z9PanicExitv+0xf)[0x5605350426df]
./bladebit_cuda(_ZN15GpuUploadBuffer11UploadArrayEPKvjjjjPKjP11CUstream_st+0x53d)[0x560534e98f3d]
./bladebit_cuda(+0x7de3e)[0x560534e60e3e]
./bladebit_cuda(_ZN14CudaK32Plotter3RunERK11PlotRequest+0x118b)[0x560534e6754b]
./bladebit_cuda(main+0xaed)[0x560534e5e86d]
/lib/x86_64-linux-gnu/libc.so.6(__libc_start_main+0xf3)[0x7fe3bfd5a083]
./bladebit_cuda(_start+0x2e)[0x560534e6002e]