What makes cuLaunchKernel fail with CUDA_ERROR_INVALID_HANDLE?...

How can I reset the CUDA error to success with Driver API after a trap instruction?...

Unexpected CUDA_ERROR_INVALID_VALUE from cuLaunchKernel()...

ImportError: libcuda.so.1: cannot open shared object file...

Are CUDA_VERSION and CUDART_VERSION necessarily the same?...

How do the CUDA Runtime's current device and the driver context stack interact?...

What are the new unique-id's for CUDA streams and contexts useful for?...

Which Compute Capability is supported by which CUDA versions?...

Can I obtain what's used as __nv_nvrtc_builtin_header.h?...

CUDA H.265 decoder initialization fault...

What type should be pointed to for the result of cuDeviceGetGraphMemAttribute()?...

Is NVIDIA's JIT compilation cache used when you don't use NVCC?...

Why is cuMemAddressReserve() failing with CUDA_INVALID_VALUE?...

Is it possible to run cuMemset on a CUarray?...

How do I obtain the _actual_ CUDA driver version?...

How can I get the CUDA driver module handle for functions and globals in the compiled program?...

What are the types of these CUDA pointer attributes?...

Do cuDevicePrimaryCtxReset() and cudaDeviceReset() do the same thing?...

Does the CUDA JIT compiler perform device link-time optimization?...

What does cudaSetDevice() do to a CUDA device's context stack?...