[WebGPU] Add SparsePagedAttention (#32533)
### Description
Adds WebGPU Execution Provider support for
`com.microsoft.SparsePagedAttention` using the shared CPU/CUDA schema.
- **Attention**
- Supports selected main-cache reads.
- Supports local paged attention plus selected contiguous auxiliary K/V.
- Computes one FP32 softmax across local, selected, and sink logits.
- **Cache and metadata**
- Reuses PagedAttention QKV splitting, RoPE, and cache-update paths.
- Keeps selection, request metadata, and block-table resolution
device-resident.
- Supports slot mapping, suppressed writes, cache aliasing, and shared
auxiliary K/V.
- **Safety**
- Validates signed indices before unsigned conversion.
- Bounds logical positions and shader iteration counts by cache
capacity.
- Rejects unsupported types, layouts, dimensions, quantization, and
resource limits without truncation.
- **Coverage**
- Adds deterministic tests for selected-main, local-plus-auxiliary,
joint softmax, grouped-query batching, cache writes, invalid inputs, and
extreme lengths.
- Documents the supported WebGPU feature matrix and limits.
### Motivation and Context
`SparsePagedAttention` enables QSA-style selected reads and CSA-style
local-plus-compressed attention over paged caches. WebGPU support allows
these models to preserve the common operator ABI and device-resident
scheduling semantics without provider-specific graph rewrites.
---------
Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Co-authored-by: Kunal Vaishnavi <kvaishnavi@microsoft.com>
