diff --git a/scripts/stack-qwen38-official-fp8.py b/scripts/stack-qwen38-official-fp8.py
index 3604cc0..106e983 100755
--- a/scripts/stack-qwen38-official-fp8.py
+++ b/scripts/stack-qwen38-official-fp8.py
@@ -377,7 +377,14 @@ def main():
     log(f"experts stacked: {written_total / 2**30:.2f} GiB in {len(prefixes)} files")
 
     # ---- stage PLE --------------------------------------------------------
-    out_name = "ple.merged.safetensors"
+    # The file name sorts BEFORE the model-000NN shards ON PURPOSE: the reader
+    # opens every index-named file in sorted order and emplaces EVERY tensor
+    # it physically holds, first-wins (checkpoint.cpp add_shard). The raw
+    # shards carry tensors of the SAME name as the merged one
+    # (...ple.ple_embedding.ngram_embedding.shard_0.weight, [2500012,160]
+    # fp8), so ple.merged.safetensors lost the race and the plan read one raw
+    # shard as the codes. "00-" wins the sort and the name.
+    out_name = "00-ple.merged.safetensors"
     out_path = os.path.join(stage, out_name)
     data_bytes = total_rows * hd * 2
     hdr = {merged_name: {"dtype": BF16, "shape": [total_rows, hd],