Batched vision models cannot use a draft model: is_draft_model_compatible() returns False unconditionally

Nobody has claimed this yet.

## Summary

`BatchedVisionModelKit.is_draft_model_compatible()` returns `False` unconditionally, so no draft model can be selected for any multimodal MLX model. The Draft Model dropdown is permanently empty for VLMs.

https://github.com/lmstudio-ai/mlx-engine/blob/main/mlx_engine/model_kit/batched_vision/model_kit.py#L373-L384

```python
def is_draft_model_compatible(self, path: str | Path) -> bool:
return False

def load_draft_model(self, path: str | Path) -> None:
raise ValueError(
"Speculative decoding is not currently supported for batched vision models"
)
```

Model-kit dispatch selects this kit whenever `config.json` contains a `vision_config`, so it applies to every VLM, including text-only requests.

`is_speculative_decoding_supported()` rejects it a second time:

```python
def is_speculative_decoding_supported(model_kit: object) -> bool:
return type(model_kit) is ModelKit
```

https://github.com/lmstudio-ai/mlx-engine/blob/main/mlx_engine/utils/speculative_decoding.py#L15

Related issues:

- https://github.com/lmstudio-ai/mlx-engine/issues/269 / #272 — same gate for `BatchedModelKit` (text), fixed via the `max_seq_nums == 1` escape hatch. Vision kits have no equivalent.
- https://github.com/lmstudio-ai/mlx-engine/issues/343 — `mtp.*` sidecar strict-load failure. A loading bug, explicitly not acceleration.
- https://github.com/lmstudio-ai/mlx-engine/issues/323 — general MTP support.

## Environment

- LM Studio: `0.4.20+1`
- Selected MLX runtime: `mlx-llm-mac-arm64-apple-metal-advsimd@1.11.0` (also checked `1.10.1`; identical)
- Vendored `mlx_vlm`: `0.6.3`
- macOS: `26.5`, `arm64`

## Reproduction

1. Load any MLX model whose `config.json` contains a `vision_config`.
2. Open Speculative Decoding → Draft Model.

## Actual Behavior

The dropdown shows "No compatible draft models found for your current model selection" for every candidate, including a native MTP drafter split from the same base.

`is_draft_model_compatible()` returns before any comparison is performed, so drafter suitability is never evaluated.

Setting the drafter directly via `llm.prediction.speculativeDecoding.draftModel` reaches `load_draft_model()`, which raises:

```text
ValueError: Speculative decoding is not currently supported for batched vision models
```

## Expected Behavior

A matching drafter should be selectable and used, as it is on the text path.

The same base/drafter pair works through the vendored `mlx_vlm` directly:

```python
generate_step(input_ids, model, pixel_values=None, mask=None,
draft_model=drafter, draft_kind="mtp")
```

so this is a dispatch limitation rather than a model or library one.

## Notes

Enabling the flag alone is not sufficient. MTP verification needs `hidden_states[-1]` and `shared_kv_states` from the target model (`mlx_vlm/speculative/utils.py::run_speculative_rounds`), while `GenerationBatch._step()` consumes `.logits` only — the drafter would load and go unused.

I have a local patch that routes single text-only requests through `mlx_vlm`'s `generate_step` when a drafter is loaded, leaving image and concurrent requests on the stock batched path. Measured 1.77x (18.9 vs 10.7 tok/s) with byte-identical output on a 27B 6-bit VLM. It forgoes prompt-cache reuse while drafting, which is why I'm filing this rather than a PR — happy to share it if useful.

Start with mlx_engine/model_kit/batched_vision/model_kit.py around is_draft_model_compatible() and load_draft_model(), then inspect mlx_engine/utils/speculative_decoding.py and the related text-path escape hatch from issues #269 and #272. Reproduce the empty Draft Model dropdown with a VLM and trace the vendored mlx_vlm/speculative/utils.py requirements. Done means a compatible drafter can be selected and used without breaking image or concurrent requests.

Written by the indexing model from the issue text.