SYCL backend now supports GPU-resident TOP_K for large k.

The official source reports this update: b10956: sycl: rfc: Use radix select for top_k. sycl: rfc: Use radix select for top_k ( #28670 ) sycl: GPU-resident TOP_K for large k, parallelised over the device The SYCL backend refused GGML_OP_TOP_K above k = 32 and let it fall back to the CPU, a backend round-trip per call. The limit was not conservatism: the scan-merge kernels keep (split_block + 1) * k candidate (value, index) pairs in SLM, so at k = 128 a work-group already needs 132 KB and cannot launch. qwen4exp's sparse-attention indexer asks for k = 2048 in 12 layers on every token, so this fired at every context length. Add a radix select for large k.