FP16转换报错的原因？

FP32转换正常，FP16转换报错（model_transform正常）
运行命令为：
model_deploy.py         --mlir omniSR-DIV4x-simplify.mlir         --quantize F16         --chip bm1684x         --model omniSR-DIV4x-simplify.bmodel

报错信息：
[ERR] /workspace/nntoolchain/TPU1686/firmware_core/src/local_layer/nodechip_group_norm_local.c:1072: nodechip_layer_norm_local: Assertion "0 < axis    axis < 5" failed.
Obtained 10 stack frames.
/workspace/tpu-mlir_v1.2.8-g32d7b3ec-20230802/lib/libbackend_1684x.so(+0x3194f3) [0x7fafc50964f3]
/workspace/tpu-mlir_v1.2.8-g32d7b3ec-20230802/lib/libbackend_1684x.so(__print_trace+0xe) [0x7fafc5096579]
/workspace/tpu-mlir_v1.2.8-g32d7b3ec-20230802/lib/libbackend_1684x.so(nodechip_layer_norm_local+0x8d) [0x7fafc4f92248]
/workspace/tpu-mlir_v1.2.8-g32d7b3ec-20230802/lib/libbackend_1684x.so(api_layer_norm_local+0x1e3) [0x7fafc4f691d9]
/workspace/tpu-mlir_v1.2.8-g32d7b3ec-20230802/lib/libbackend_1684x.so(backend_api_layer_norm_local+0xe0) [0x7fafc4e065b0]
tpuc-opt(+0x4cb959) [0x5631b7ccb959]
tpuc-opt(+0x402c30) [0x5631b7c02c30]
tpuc-opt(+0x6f76ca) [0x5631b7ef76ca]
tpuc-opt(+0x5b305c) [0x5631b7db305c]
tpuc-opt(+0x5b37ab) [0x5631b7db37ab]
Traceback (most recent call last):
  File "/workspace/tpu-mlir_v1.2.8-g32d7b3ec-20230802/python/tools/model_deploy.py", line 288, in
    tool.build_model()
  File "/workspace/tpu-mlir_v1.2.8-g32d7b3ec-20230802/python/tools/model_deploy.py", line 202, in build_model
    self.op_divide
  File "/workspace/tpu-mlir_v1.2.8-g32d7b3ec-20230802/python/utils/mlir_shell.py", line 154, in mlir_to_model
    _os_system(cmd)
  File "/workspace/tpu-mlir_v1.2.8-g32d7b3ec-20230802/python/utils/mlir_shell.py", line 50, in _os_system
    raise RuntimeError("[!Error]: {}".format(cmd_str))
RuntimeError: [!Error]: tpuc-opt omniSR-DIV4x-simplify_bm1684x_f16_final.mlir --codegen="model_file=omniSR-DIV4x-simplify.bmodel" -o /dev/null