diff --git a/crates/ml/src/cuda_pipeline/batched_backward.rs b/crates/ml/src/cuda_pipeline/batched_backward.rs
index 5010058e2..7f5fd0f23 100644
--- a/crates/ml/src/cuda_pipeline/batched_backward.rs
+++ b/crates/ml/src/cuda_pipeline/batched_backward.rs
@@ -815,7 +815,7 @@ impl CublasBackwardSet {
         // We compute these inline from the config dimensions.
         // grad_buf is now f32, so byte offsets use sizeof(f32) = 4.
         let f32 = std::mem::size_of::<f32>() as u64;
-        let sd = self.state_dim as u64;
+        let s1d = self.s1_input_dim as u64; // CRITICAL: must match compute_param_sizes (not state_dim)
         let sh1 = self.shared_h1 as u64;
         let sh2 = self.shared_h2 as u64;
         let vh = self.value_h as u64;
@@ -828,7 +828,7 @@ impl CublasBackwardSet {
 
         // GOFF byte offsets (must match compute_param_sizes order)
         let goff_w_s1:    u64 = 0;
-        let goff_b_s1:    u64 = goff_w_s1    + sh1 * sd         * f32;
+        let goff_b_s1:    u64 = goff_w_s1    + sh1 * s1d        * f32;
         let goff_w_s2:    u64 = goff_b_s1    + sh1              * f32;
         let goff_b_s2:    u64 = goff_w_s2    + sh2 * sh1        * f32;
         let goff_w_v1:    u64 = goff_b_s2    + sh2              * f32;
diff --git a/crates/ml/src/cuda_pipeline/gpu_dqn_trainer.rs b/crates/ml/src/cuda_pipeline/gpu_dqn_trainer.rs
index 39f6a847c..a7fa40a57 100644
--- a/crates/ml/src/cuda_pipeline/gpu_dqn_trainer.rs
+++ b/crates/ml/src/cuda_pipeline/gpu_dqn_trainer.rs
@@ -2694,7 +2694,8 @@ impl GpuDqnTrainer {
         info!("GpuDqnTrainer: mag_concat_qdir + strided_accumulate kernels loaded");
 
         // ── Cross-Branch Q Attention buffers ──────────────────────────
-        let q_attn_params = alloc_f32(&stream, 624, "q_attn_params")?;
+        let q_attn_params = stream.alloc_zeros::<f32>(624)
+            .map_err(|e| MLError::ModelError(format!("alloc q_attn_params: {e}")))?;
         let q_attn_adam_m = stream.alloc_zeros::<f32>(624)
             .map_err(|e| MLError::ModelError(format!("alloc q_attn_adam_m: {e}")))?;
         let q_attn_adam_v = stream.alloc_zeros::<f32>(624)