Cannot run dali model in deepstream-triton 5.1.21.2

Same model, i am successful run on trition server 20.11. But when i ran on deepstream-trition 5.1.21.2, there is an error related to tag version.
E0716 06:43:17.929970 5269 logging.cc:43] coreReadArchive.cpp (32) - Serialization Error in verifyHeader: 0 (Magic tag does not match)
E0716 06:43:17.930068 5269 logging.cc:43] INVALID_STATE: std::exception
E0716 06:43:17.930074 5269 logging.cc:43] INVALID_CONFIG: Deserialize the cuda engine failed.
W0716 06:43:17.930082 5269 autofill.cc:225] Autofiller failed to detect the platform for retinaface_preprocess (verify contents of model directory or use --log-verbose=1 for more details)
W0716 06:43:17.930086 5269 autofill.cc:248] Proceeding with simple config for now
I0716 06:43:17.930418 5269 model_repository_manager.cc:810] loading: retinaface_preprocess:1
E0716 06:43:17.941151 5269 model_repository_manager.cc:986] failed to load 'retinaface_preprocess' version 1: Not found: unable to load backend library: /usr/lib/x86_64-linux-gnu/libstdc++.so.6: cannot allocate memory in static TLS block
ERROR: infer_trtis_server.cpp:1044 Triton: failed to load model retinaface_preprocess, triton_err_str:Invalid argument, err_msg:load failed for model 'retinaface_preprocess': version 1: Not found: unable to load backend library: /usr/lib/x86_64-linux-gnu/libstdc++.so.6: cannot allocate memory in static TLS block;

ERROR: infer_trtis_backend.cpp:45 failed to load model: retinaface_preprocess, nvinfer error:NVDSINFER_TRTIS_ERROR
ERROR: infer_trtis_backend.cpp:184 failed to initialize backend while ensuring model:retinaface_preprocess ready, nvinfer error:NVDSINFER_TRTIS_ERROR
0:00:09.727932979  5269      0x4ab4780 ERROR          nvinferserver gstnvinferserver.cpp:362:gst_nvinfer_server_logger:<primary-inference> nvinferserver[UID 5]: Error in createNNBackend() <infer_trtis_context.cpp:246> [UID = 5]: failed to initialize trtis backend for model:retinaface_preprocess, nvinfer error:NVDSINFER_TRTIS_ERROR
I0716 06:43:17.941406 5269 server.cc:280] Waiting for in-flight requests to complete.
I0716 06:43:17.941431 5269 server.cc:295] Timeout 30: Found 0 live models and 0 in-flight non-inference requests
0:00:09.728082338  5269      0x4ab4780 ERROR          nvinferserver gstnvinferserver.cpp:362:gst_nvinfer_server_logger:<primary-inference> nvinferserver[UID 5]: Error in initialize() <infer_base_context.cpp:81> [UID = 5]: create nn-backend failed, check config file settings, nvinfer error:NVDSINFER_TRTIS_ERROR
0:00:09.728095248  5269      0x4ab4780 WARN           nvinferserver gstnvinferserver_impl.cpp:439:start:<primary-inference> error: Failed to initialize InferTrtIsContext
0:00:09.728099778  5269      0x4ab4780 WARN           nvinferserver gstnvinferserver_impl.cpp:439:start:<primary-inference> error: Config file path: /data/deepstream-retinaface/dstest_ssd_nopostprocess.txt
0:00:09.728476338  5269      0x4ab4780 WARN           nvinferserver gstnvinferserver.cpp:460:gst_nvinfer_server_start:<primary-inference> error: gstnvinferserver_impl start failed
Error: gst-resource-error-quark: Failed to initialize InferTrtIsContext (1): gstnvinferserver_impl.cpp(439): start (): /GstPipeline:pipeline0/GstNvInferServer:primary-inference:
How do i fix this problem?
triton-inference-server / dali_backend

Cannot run dali model in deepstream-triton 5.1.21.2 #87
