Documented return types in cudart.pyx are inconsistent with implementation.

[bdice]

The function signature of many APIs in the docs appear to return a 2-tuple like (status, None) but the actual return value is a 1-tuple like (status,).

For example:
Docs link: https://nvidia.github.io/cuda-python/api.html#cuda.cudart.cudaSetDevice
Source:

cuda-python/cuda/cudart.pyx

Lines 7903 to 7910 in d7a354d

	Returns
	-------
	cudaError_t
	cudaSuccess
	cudaErrorInvalidDevice
	cudaErrorDeviceAlreadyInUse
	None
	None

Rendered docs:

In some cases, there is a second element like a string or memory pool in the tuple but the documented type indicates it as None.

For example:

cuda-python/cuda/cudart.pyx

Lines 7164 to 7193 in d7a354d

	def cudaGetErrorName(error not None : cudaError_t):
	""" Returns the string representation of an error code enum name.
	Returns a string containing the name of an error code in the enum. If
	the error code is not recognized, "unrecognized error code" is
	returned.
	Parameters
	----------
	error : cudaError_t
	Error code to convert to string
	Returns
	-------
	cudaError_t
	`char*` pointer to a NULL-terminated string
	None
	None
	See Also
	--------
	cudaGetErrorString
	cudaGetLastError
	cudaPeekAtLastError
	cudaError
	cuGetErrorName
	"""
	cdef ccudart.cudaError_t cerror = error.value
	err = ccudart.cudaGetErrorName(cerror)
	return (cudaError_t.cudaSuccess, err)

cuda-python/cuda/cudart.pyx

Lines 7641 to 7670 in d7a354d

	def cudaDeviceGetDefaultMemPool(int device):
	""" Returns the default mempool of a device.
	The default mempool of a device contains device memory from that
	device.
	Returns
	-------
	cudaError_t
	cudaSuccess
	cudaErrorInvalidDevice
	cudaErrorInvalidValue
	cudaErrorNotSupported
	None
	None
	See Also
	--------
	cuDeviceGetDefaultMemPool
	cudaMallocAsync
	cudaMemPoolTrimTo
	cudaMemPoolGetAttribute
	cudaDeviceSetMemPool
	cudaMemPoolSetAttribute
	cudaMemPoolSetAccess
	"""
	cdef cudaMemPool_t memPool = cudaMemPool_t()
	with nogil:
	err = ccudart.cudaDeviceGetDefaultMemPool(<ccudart.cudaMemPool_t*>memPool._ptr, device)
	return (cudaError_t(err), memPool)

Let me know if you'd like me to work on this issue. I would be happy to contribute a pull request to improve the docs. 👍 I see PRs are not currently accepted.

[vzhurba01]

Thanks for the notice! Fix submitted.

[bdice]

Thank you @vzhurba01! 😊