Reduce KV memory for local-attention layers

## Problem

On `dev` (`1658f88`), the default `flash` attention path reserves full-context BF16 KV/K/V storage for local and global layers alike. Local layers only attend to their sliding window, so retaining capacity for the entire context wastes memory as the configured context grows.

The runtime-aware cache constructor also allocates compact tiled buffers that the default Flash path does not use. The tiled attention backends already have compact local rings; the default Flash path still reads the legacy transposed K/V buffers.

## Fix direction

- Allocate separate BF16 buffers per owning layer for the default Flash path.
- Size local rings for the attention window plus the full prefill batch and trailing SIMD padding, capped by the configured context. The extra rows prevent batch writes and padding from overwriting history needed by early queries.
- Keep global layers at the configured context capacity, with the logical context limit separate from physical alignment padding.
- Reuse the source layer's buffers for shared-KV layers and retain the largest window required by their consumers.
- Preserve live history when runtime batches require larger rings, keep snapshots independent, and clear buffers safely when reusing a cache.
- Allocate only the buffers used by the selected attention backend and preserve the existing BF16 attention arithmetic and model-specific cache layouts.

Start by locating the runtime-aware cache constructor, the default Flash attention path, and the tiled attention backends described in the issue. Trace how local and global layers allocate and read BF16 K/V buffers, then verify that resizing, snapshots, cache reuse, shared-KV layers, and backend selection preserve history and existing attention behavior.

Scritto dal modello di indicizzazione a partire dal testo della issue.