NVIDIA-AI-IOT
no kernel image is available for execution on the device （libspconv.so (aarch64_cuda12.8)）
Thank you for releasing libspconv.so (aarch64_cuda12.8). An error occurred when executing "bash tool/run.sh".
[rulebook.cu:273] (Error) CUDA Runtime error spconv::setup_hash_and_route<<<(num_input + 1023) / 1024, 1024, 0, stream>>>( hash_.get(), route_mask_.ptr(), route_.ptr(), indices, num_input, prob->kv) # no kernel image is available for execution on the device, code = cudaErrorNoKernelImageForDevice [ 209 ] in file src/spconv/rulebook.cu:273 tool/run.sh: line 44: 5816 Aborted (core dumped) ./build/bevfusion $DEBUG_DATA $DEBUG_MODEL $DEBUG_PRECISION
I have uploaded the libspconv that supports SM87. Please give the new one a try. Thank you!
I have uploaded the libspconv that supports SM87. Please give the new one a try. Thank you!
Hi, thank you for providing the new libspconv with SM87 support!
I would like to ask:
Is this spconv library built from the source code of https://github.com/traveller59/spconv?
If I want to compile a version of the library that supports SM_10x, which tag or version of spconv should I use to replace the library under lidarbries/3DSparseConvolution/libspconv?
Thank you very much for your help!
@hopef hi, I compiled and ran bevfusion on the latest libspconv ，can get detection results, but there are errors in the run log.
I have uploaded the libspconv that supports SM87. Please give the new one a try. Thank you!
I couldn't find a suitable libspconv for sm_87, and it still reports an error when I run it.#350
