diff --git a/tileops/manifest/linear_attention.yaml b/tileops/manifest/linear_attention.yaml
index 4d817f1fa..a27bc8027 100644
--- a/tileops/manifest/linear_attention.yaml
+++ b/tileops/manifest/linear_attention.yaml
@@ -23,7 +23,8 @@ GatedDeltaNetPrefillFwdOp:
       o: {dtype: "same_as(q)"}
       final_state: {dtype: "same_as(q)"}
     params:
-      chunk_size: {type: int, default: 64}
+      chunk_size: {type: "int | None", default: null}
+      layout: {type: str, default: "bhtd"}
     shape_rules:
       - "q.shape == (B, H, S, DK)"
       - "k.shape == (B, H, S, DK)"
@@ -32,13 +33,14 @@ GatedDeltaNetPrefillFwdOp:
       - "beta.shape == (B, H, S)"
       - "o.shape == (B, H, S, DV)"
       - "final_state.shape == (B, H, DK, DV)"
-      - "S % chunk_size == 0"
+      - "chunk_size is None or S % chunk_size == 0"
 
   workloads:
     # Inference-oriented BHSD rows. Unit tests should use smaller
     # branch-covering shapes in tests/ops, not these benchmark workloads.
     - {q_shape: [1, 16, 512, 128], k_shape: [1, 16, 512, 128], v_shape: [1, 16, 512, 128], g_shape: [1, 16, 512], beta_shape: [1, 16, 512], chunk_size: 64, dtypes: [float16, bfloat16], label: "gdn-prefill-b1-s512-h16-d128"}
     - {q_shape: [4, 16, 2048, 64], k_shape: [4, 16, 2048, 64], v_shape: [4, 16, 2048, 128], g_shape: [4, 16, 2048], beta_shape: [4, 16, 2048], chunk_size: 64, dtypes: [float16, bfloat16], label: "gdn-prefill-b4-s2k-h16-dk64-dv128"}
+    - {q_shape: [1, 16, 2048, 128], k_shape: [1, 16, 2048, 128], v_shape: [1, 16, 2048, 128], g_shape: [1, 16, 2048], beta_shape: [1, 16, 2048], chunk_size: 64, dtypes: [float16, bfloat16], label: "gdn-prefill-b1-s2k-h16-d128"}
     - {q_shape: [1, 16, 8192, 128], k_shape: [1, 16, 8192, 128], v_shape: [1, 16, 8192, 128], g_shape: [1, 16, 8192], beta_shape: [1, 16, 8192], chunk_size: 64, dtypes: [float16, bfloat16], label: "gdn-prefill-b1-s8k-h16-d128"}
 
   roofline: