diff --git a/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanBatchPrefillDecode.java b/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanBatchPrefillDecode.java
index a0fb1c1b..e80e757f 100644
--- a/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanBatchPrefillDecode.java
+++ b/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanBatchPrefillDecode.java
@@ -78,21 +78,28 @@ public TornadoExecutionPlan createExecutionPlan() {
 
     // ── Initialisation ────────────────────────────────────────────────────────
 
+    /**
+     * Puts the read-only weights on the device. With CUDA graphs enabled the pass is also the
+     * capture, so it still runs every graph; otherwise it is a plain copy-in and no kernel runs.
+     */
     // @formatter:off
     @Override
     public void forceCopyInReadOnlyData() {
+        if (!CUDA_GRAPHS) {
+            executionPlan.transferToDevice();
+            return;
+        }
+
         state.wrapX.clear();
         state.positionHolder.init(0);
         state.wrapXBatch.clear();
         state.batchStartPosHolder.init(0);
 
         for (int i = 0; i <= taskGraphLayout.logitsIdx(); i++) {
-            var g = executionPlan.withGraph(i)
-                                 .withGridScheduler(batchPrefillDecodeForwardPlan.getGridScheduler());
-            if (CUDA_GRAPHS) {
-                g.withCUDAGraph();
-            }
-            g.execute();
+            executionPlan.withGraph(i)
+                         .withGridScheduler(batchPrefillDecodeForwardPlan.getGridScheduler())
+                         .withCUDAGraph()
+                         .execute();
         }
     }
     // @formatter:on
diff --git a/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanPrefillDecode.java b/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanPrefillDecode.java
index 4ba9c834..73f9f47d 100644
--- a/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanPrefillDecode.java
+++ b/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanPrefillDecode.java
@@ -86,20 +86,26 @@ public TornadoExecutionPlan createExecutionPlan() {
 
     // ── Initialisation ────────────────────────────────────────────────────────
 
-    /** Runs all graphs once to trigger FIRST_EXECUTION uploads and warm up CUDA graphs. */
+    /**
+     * Puts the read-only weights on the device. With CUDA graphs enabled the pass is also the
+     * capture, so it still runs every graph; otherwise it is a plain copy-in and no kernel runs.
+     */
     // @formatter:off
     @Override
     public void forceCopyInReadOnlyData() {
+        if (!CUDA_GRAPHS) {
+            executionPlan.transferToDevice();
+            return;
+        }
+
         state.wrapX.clear();
         state.positionHolder.init(0);
 
         for (int i = 0; i <= taskGraphLayout.logitsIdx(); i++) {
-            var g = executionPlan.withGraph(i)
-                                 .withGridScheduler(prefillDecodeForwardPlan.getGridScheduler());
-            if (CUDA_GRAPHS) {
-                g.withCUDAGraph();
-            }
-            g.execute();
+            executionPlan.withGraph(i)
+                         .withGridScheduler(prefillDecodeForwardPlan.getGridScheduler())
+                         .withCUDAGraph()
+                         .execute();
         }
     }
     // @formatter:on
diff --git a/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanSingleToken.java b/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanSingleToken.java
index 5035d384..df8aa0ad 100644
--- a/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanSingleToken.java
+++ b/src/main/java/org/beehive/gpullama3/tornadovm/TornadoVMMasterPlanSingleToken.java
@@ -95,9 +95,18 @@ public FloatArray tornadoVMForwardDecode(int position) {
     }
     // @formatter:on
 
+    /**
+     * Puts the read-only weights on the device. With CUDA graphs enabled the pass is also the
+     * capture, so it still runs every graph; otherwise it is a plain copy-in and no kernel runs.
+     */
     // @formatter:off
     @Override
     public void forceCopyInReadOnlyData() {
+        if (!CUDA_GRAPHS) {
+            executionPlan.transferToDevice();
+            return;
+        }
+
         state.wrapX.clear();
         state.positionHolder.init(0);