Need help in fixing the error from running the edge model.

[himalayjor]

I am using this docs to test my output edge model saved on disk.

https://pytorch.org/executorch/stable/runtime-python-api-reference.html#executorch.runtime.Runtime

I get the following stack-trace which doesn't help much in debugging. There is no reference to computation graph which can help in debugging. What can I do fix this ?

E 00:00:00.223620 executorch:method_meta.cpp:169] Tag: 0 output: 2 is not Tensor
E 00:00:00.223647 executorch:pybindings.cpp:938] Tensor meta doesn't exist for output 2, error is 0x12, skipping allocating storage
E 00:00:00.223654 executorch:method_meta.cpp:169] Tag: 0 output: 4 is not Tensor
E 00:00:00.223658 executorch:pybindings.cpp:938] Tensor meta doesn't exist for output 4, error is 0x12, skipping allocating storage
E 00:00:00.223663 executorch:method_meta.cpp:169] Tag: 0 output: 5 is not Tensor
E 00:00:00.223666 executorch:pybindings.cpp:938] Tensor meta doesn't exist for output 5, error is 0x12, skipping allocating storage
E 00:00:00.223672 executorch:tensor_impl.cpp:105] Attempted to resize a bounded tensor with capacity of 128000 elements to 64000 elements.
E 00:00:00.223676 executorch:method.cpp:803] Error setting input 0: 0x10
Traceback (most recent call last):
  File "/home/himalay.joriwal/test_model_output.pte", line 19, in <module>
    outputs = forward.execute(inputs)
              ^^^^^^^^^^^^^^^^^^^^^^^
  File "/home/himalay.joriwal/.conda/envs/uat/lib/python3.11/site-packages/executorch/runtime/__init__.py", line 79, in execute
    return self._module.run_method(self._method_name, inputs)
           ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
RuntimeError: method->set_inputs() for method 'forward' failed with error 0x12

My environment settings.

(uat) himalay.joriwal@scl-c32-r16-svr02:~$ python3 -m torch.utils.collect_env
<frozen runpy>:128: RuntimeWarning: 'torch.utils.collect_env' found in sys.modules after import of package 'torch.utils', but prior to execution of 'torch.utils.collect_env'; this may result in unpredictable behaviour
Collecting environment information...
PyTorch version: 2.5.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.5 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.22.1
Libc version: glibc-2.35

Python version: 3.11.11 (main, Dec 11 2024, 16:28:39) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-125-generic-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.6.85
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: 
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3

Nvidia driver version: 550.127.05
cuDNN version: Could not collect
HIP runtime version: N/A
MIOpen runtime version: N/A
Is XNNPACK available: True

CPU:
Architecture:                         x86_64
CPU op-mode(s):                       32-bit, 64-bit
Address sizes:                        46 bits physical, 57 bits virtual
Byte Order:                           Little Endian
CPU(s):                               224
On-line CPU(s) list:                  0-223
Vendor ID:                            GenuineIntel
Model name:                           Intel(R) Xeon(R) Platinum 8480+
CPU family:                           6
Model:                                143
Thread(s) per core:                   2
Core(s) per socket:                   56
Socket(s):                            2
Stepping:                             8
BogoMIPS:                             4000.00
Flags:                                fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl vmx smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 invpcid_single cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Virtualization:                       VT-x
L1d cache:                            5.3 MiB (112 instances)
L1i cache:                            3.5 MiB (112 instances)
L2 cache:                             224 MiB (112 instances)
L3 cache:                             210 MiB (2 instances)
NUMA node(s):                         2
NUMA node0 CPU(s):                    0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110,112,114,116,118,120,122,124,126,128,130,132,134,136,138,140,142,144,146,148,150,152,154,156,158,160,162,164,166,168,170,172,174,176,178,180,182,184,186,188,190,192,194,196,198,200,202,204,206,208,210,212,214,216,218,220,222
NUMA node1 CPU(s):                    1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111,113,115,117,119,121,123,125,127,129,131,133,135,137,139,141,143,145,147,149,151,153,155,157,159,161,163,165,167,169,171,173,175,177,179,181,183,185,187,189,191,193,195,197,199,201,203,205,207,209,211,213,215,217,219,221,223
Vulnerability Gather data sampling:   Not affected
Vulnerability Itlb multihit:          Not affected
Vulnerability L1tf:                   Not affected
Vulnerability Mds:                    Not affected
Vulnerability Meltdown:               Not affected
Vulnerability Mmio stale data:        Not affected
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed:               Not affected
Vulnerability Spec rstack overflow:   Not affected
Vulnerability Spec store bypass:      Mitigation; Speculative Store Bypass disabled via prctl and seccomp
Vulnerability Spectre v1:             Mitigation; usercopy/swapgs barriers and __user pointer sanitization
Vulnerability Spectre v2:             Mitigation; Enhanced / Automatic IBRS; IBPB conditional; RSB filling; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S
Vulnerability Srbds:                  Not affected
Vulnerability Tsx async abort:        Not affected

Versions of relevant libraries:
[pip3] executorch==0.4.0
[pip3] flake8==5.0.4
[pip3] k2==1.24.4.dev20241030+cuda12.4.torch2.5.0
[pip3] kaldifeat==1.25.5.dev20241030+cuda12.4.torch2.5.0
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.23.2
[pip3] onnx==1.17.0
[pip3] onnxconverter-common==1.14.0
[pip3] onnxoptimizer==0.3.13
[pip3] onnxruntime==1.20.1
[pip3] onnxsim==0.4.36
[pip3] pytorch-lightning==2.5.0.post0
[pip3] torch==2.5.0
[pip3] torchaudio==2.5.0
[pip3] torchmetrics==1.6.1
[pip3] torchvision==0.20.0
[pip3] triton==3.1.0
[conda] executorch                0.4.0                    pypi_0    pypi
[conda] k2                        1.24.4.dev20241030+cuda12.4.torch2.5.0          pypi_0    pypi
[conda] kaldifeat                 1.25.5.dev20241030+cuda12.4.torch2.5.0          pypi_0    pypi
[conda] numpy                     1.23.2                   pypi_0    pypi
[conda] pytorch-lightning         2.5.0.post0              pypi_0    pypi
[conda] torch                     2.5.0                    pypi_0    pypi
[conda] torchaudio                2.5.0                    pypi_0    pypi
[conda] torchmetrics              1.6.1                    pypi_0    pypi
[conda] torchvision               0.20.0                   pypi_0    pypi
[conda] triton                    3.1.0                    pypi_0    pypi

This are the steps to produce the edge model where I use dynamic_shapes for the model.

       aten_dialect = export(encode_wrapper, (x, x_lens), dynamic_shapes=dynamic_shapes)

        # Step 2: Optimize for edge devices
        #edge_program = to_edge(aten_dialect)

        edge_program = to_edge(aten_dialect, compile_config=EdgeCompileConfig(_core_aten_ops_exception_list=[torch.ops.aten._assert_scalar.default]))

        # Step 3: Convert to ExecuTorch program
        executorch_program = edge_program.to_executorch()

        # Step 4: Save the compiled .pte program if a file path is provided
        if file_path is not None:
            with open(file_path, "wb") as file:
                file.write(executorch_program.buffer)
        return executorch_program

[tarun292]

@himalayjor are all the outputs of your model Tensors? If not can you convert them to Tensors before returning the output?