Bound winograd conv2d working set by tiling the batch

[Gusanidas]

Addresses the conv2d manifestation of #3979 — the conv-side guard, not a fix for the general silent-error mechanism.

Problem

conv2d on Metal silently returns all zeros for large batched inputs. The Winograd path keeps the padded input and both GEMM workspaces alive at once (~3.7x the input for the reported shapes), all referenced by one command buffer; once that working set exceeds recommendedMaxWorkingSetSize the driver fails the command buffer. As @jasonge27's instrumentation shows, Metal reports the OOM but errors from mid-eval commits are dropped, so nothing surfaces. Winograd's selection criteria (C % 32 == 0 && O % 32 == 0 && C + O >= 256) explain the channel dependence in the report. That dropped-error mechanism is general and needs a separate, complementary fix in the eval machinery; this PR avoids the OOM for conv2d, which also bounds its peak memory.

Fix

Run the batch in tiles sized from the available working set, reusing one set of scratch buffers across tiles — mirroring the row tiling in explicit_gemm_conv_ND_gpu. The budget is 3/4 of recommendedMaxWorkingSetSize minus MLX's active memory and the transformed filter's allocation: measured failures start at ~99% of the reported limit, and the quarter held back is headroom for memory not charged by this estimate, including pressure from other processes and allocator-cached buffers. Charging all active memory deliberately over-counts unrelated buffers, erring toward smaller tiles or an earlier fallback.

When the whole batch fits, the common case, the emitted work is unchanged. It falls back to the scratch-free implicit GEMM when not even one batch element fits, or when tiles would carry too few GEMM rows to amortize their fixed cost (small tiles can be far slower than the fallback).

Testing

The real threshold needs tens of GB, so tests shrink the budget instead:

• MLX_CONV_WINOGRAD_WORKING_SET injects the byte budget: covers automatic tiling, both fallbacks, and loud rejection of malformed values.
• MLX_CONV_WINOGRAD_TILE_BATCH forces a tile size (capped by the budget): covers uniform tiles, a short final tile, and a consumer op reading the tiled output in the same eval.

At real sizes on a 96 GB M2 Max: the issue's repro passes (previously all-zero at batch 80 on this machine; the reporter hit it at batch 40 on 48 GB), tiled vs untiled outputs are bit-identical at ~50 GB scale, CPU cross-checks agree, and the batch-80 repro peaks at 58 GB where untiled Winograd would need ~84 GB. On the reported fp32 shape (40x512x512, 192 -> 96 channels) Winograd runs ~1.7x faster than implicit GEMM (310 ms vs 536 ms), while a spatially tiny conv (256x4x4, 64 -> 192) cut into one-element Winograd tiles is ~40x slower than implicit GEMM — the two sides of the tile-versus-fallback trade-off. Mid-size Winograd shapes select a single tile and show no regression.