diff --git a/deepspec/eval/dspark/evaluator.py b/deepspec/eval/dspark/evaluator.py
index eba2b34..ffc4fd0 100644
--- a/deepspec/eval/dspark/evaluator.py
+++ b/deepspec/eval/dspark/evaluator.py
@@ -88,12 +88,32 @@ class Qwen3DSparkEvaluator(BaseEvaluator):
         initial_output,
         **kwargs,
     ) -> SimpleNamespace:
+        import os
+        _w = int(os.environ.get("DSPARK_DRAFT_CTX_WINDOW", "0"))
+        target_hidden_states = extract_context_feature(
+            initial_output.hidden_states,
+            self.draft_model.target_layer_ids,
+        )
+        if _w:
+            from deepspec.eval.windowed_cache import make_draft_cache
+            past_key_values_draft = make_draft_cache(
+                self.draft_model, _w, pad=int(self.max_proposal_tokens) + 64
+            )
+            # window the init context tensor (its 5-layer hidden states are the big init spike) and
+            # offset the draft cache cumulative so absolute positions stay correct downstream.
+            _num_input = int(kwargs.get("num_input_tokens", target_hidden_states.shape[1]))
+            if target_hidden_states.shape[1] > _w:
+                target_hidden_states = target_hidden_states[:, -_w:, :].contiguous()
+            # absolute offset = where the retained window starts (prefill may have pre-trimmed it)
+            _offset = _num_input - target_hidden_states.shape[1]
+            if _offset > 0:
+                for _layer in past_key_values_draft.layers:
+                    _layer.cumulative_length = _offset
+        else:
+            past_key_values_draft = DynamicCache()
         return SimpleNamespace(
-            past_key_values_draft=DynamicCache(),
-            target_hidden_states=extract_context_feature(
-                initial_output.hidden_states,
-                self.draft_model.target_layer_ids,
-            ),
+            past_key_values_draft=past_key_values_draft,
+            target_hidden_states=target_hidden_states,
         )
 
     def _propose(
@@ -164,6 +184,8 @@ class Qwen3DSparkEvaluator(BaseEvaluator):
         *,
         input_ids: torch.Tensor,
         stop_token_ids: list[int] | None,
+        stream_callback=None,
+        prefill_mm=None,
     ) -> SimpleNamespace:
         return generate_decoding_sample(
             target_model=self.target_model,
@@ -176,6 +198,9 @@ class Qwen3DSparkEvaluator(BaseEvaluator):
             propose=self._propose,
             update=self._update,
             post_verify=self._post_verify,
+            prefill_keep_hidden_layers=[0 if l == -1 else l + 1 for l in self.draft_model.target_layer_ids],
+            stream_callback=stream_callback,
+            prefill_mm=prefill_mm,
         )
 
     def evaluate(self) -> None: