[FEA]: Add support for CU_LAUNCH_ATTRIBUTE_IGNORE in LaunchConfig

[lijinf2]

Is this a duplicate?

• I confirmed there appear to be no duplicate issues for this request and that I agree to the Code of Conduct

Area

cuda.core

Is your feature request related to a problem? Please describe.

LaunchConfig does not expose CU_LAUNCH_ATTRIBUTE_IGNORE (id = 0), the sentinel that marks an unused CUlaunchAttribute slot for the driver to skip.

Parent tracking: #496.

Describe the solution you'd like

• Users can set CU_LAUNCH_ATTRIBUTE_IGNORE via LaunchConfig.
• Mapping to the native launch attribute is tested.

Describe alternatives you've considered

Use cuda.bindings.driver (CUlaunchAttribute / CU_LAUNCH_ATTRIBUTE_IGNORE) and cuLaunchKernelEx directly.

Downside: leaves cuda.core users without a first-class LaunchConfig API; they must drop to low-level bindings, manage the attribute array themselves, and lose consistency with other LaunchConfig launch attributes (is_cooperative, programmatic_stream_serialization, etc.).

Additional context

Incremental LaunchConfig attribute coverage under #496 (same approach as #1334 for programmatic_stream_serialization).

Example (C API) — agent-generated; reviewed but not executed:

// Fixed-size attribute array; unused slots marked IGNORE
CUlaunchAttribute attrs[4];

attrs[0].id = CU_LAUNCH_ATTRIBUTE_COOPERATIVE;
attrs[0].value.cooperative = 1;

attrs[1].id = CU_LAUNCH_ATTRIBUTE_PRIORITY;
attrs[1].value.priority = 0;

attrs[2].id = CU_LAUNCH_ATTRIBUTE_IGNORE;
attrs[3].id = CU_LAUNCH_ATTRIBUTE_IGNORE;

CUlaunchConfig config = {
    .gridDimX = 128, .gridDimY = 1, .gridDimZ = 1,
    .blockDimX = 256, .blockDimY = 1, .blockDimZ = 1,
    .sharedMemBytes = 0,
    .hStream = stream,
    .attrs = attrs,
    .numAttrs = 4
};
cuLaunchKernelEx(&config, kernel, NULL, NULL);