Open
Description
🐛 Describe the bug
I tried below code to export EfficientFormer distributed by timm.
After torch.export.export is done on the model, I also tried inference by forward on the model.
It resulted in FakeTensor, where it's meant to be Tensor.
import timm, torch
model: timm.models.efficientformer.EfficientFormer = (
timm.create_model("efficientformer_l1", pretrained=True).to("cpu")
)
example_inputs = (torch.randn(1, 3, 224, 224),)
exported = torch.export.export(
model.eval(), args=example_inputs,
)
res = model.forward(*example_inputs)
print(res) # IT'S "FakeTensor"!!!Seemingly, the original torch model is affected by torch.export.export which is not expected at all.
I suspect BatchNorm in EfficientFormer - its running_mean or running_var may have changed into FakeTensor during export.
However, I failed to reproduce it with simpler model with BatchNorm-only.
Versions
PyTorch version: 2.6.0+cu124
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A
OS: Ubuntu 20.04.6 LTS (x86_64)
GCC version: (Ubuntu 9.4.0-1ubuntu1~20.04.2) 9.4.0
Clang version: 10.0.0-4ubuntu1
CMake version: version 3.16.3
Libc version: glibc-2.31
Python version: 3.10.14 (main, May 6 2024, 19:42:50) [GCC 11.2.0] (64-bit runtime)
Python platform: Linux-5.15.0-130-generic-x86_64-with-glibc2.31
Is CUDA available: True
CUDA runtime version: 12.6.85
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA GeForce RTX 2080 Ti
Nvidia driver version: 560.35.03
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
Byte Order: Little Endian
Address sizes: 46 bits physical, 48 bits virtual
CPU(s): 32
On-line CPU(s) list: 0-31
Thread(s) per core: 2
Core(s) per socket: 16
Socket(s): 1
NUMA node(s): 1
Vendor ID: GenuineIntel
CPU family: 6
Model: 85
Model name: Intel(R) Core(TM) i9-9960X CPU @ 3.10GHz
Stepping: 4
CPU MHz: 4413.371
CPU max MHz: 4600.0000
CPU min MHz: 1200.0000
BogoMIPS: 6199.99
Virtualization: VT-x
L1d cache: 512 KiB
L1i cache: 512 KiB
L2 cache: 16 MiB
L3 cache: 22 MiB
NUMA node0 CPU(s): 0-31
Vulnerability Gather data sampling: Mitigation; Microcode
Vulnerability Itlb multihit: KVM: Mitigation: VMX disabled
Vulnerability L1tf: Mitigation; PTE Inversion; VMX conditional cache flushes, SMT vulnerable
Vulnerability Mds: Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Meltdown: Mitigation; PTI
Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable
Vulnerability Reg file data sampling: Not affected
Vulnerability Retbleed: Mitigation; IBRS
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; IBRS; IBPB conditional; STIBP conditional; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected
Vulnerability Srbds: Not affected
Vulnerability Tsx async abort: Mitigation; Clear CPU buffers; SMT vulnerable
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 pni pclmulqdq dtes64 monitor ds_cpl vmx 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 cdp_l3 invpcid_single pti ssbd mba ibrs ibpb stibp tpr_shadow vnmi flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 hle avx2 smep bmi2 erms invpcid rtm cqm mpx rdt_a avx512f avx512dq rdseed adx smap clflushopt clwb intel_pt avx512cd avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local dtherm ida arat pln pts md_clear flush_l1d arch_capabilities
Versions of relevant libraries:
[pip3] ai-edge-torch==0.3.0
[pip3] flake8==6.0.0
[pip3] flake8-breakpoint==1.1.0
[pip3] flake8-bugbear==23.6.5
[pip3] flake8-comprehensions==3.12.0
[pip3] flake8-import-order==0.18.2
[pip3] flake8-plugin-utils==1.3.3
[pip3] flake8-pyi==23.5.0
[pip3] model-explorer-
[pip3] mypy==1.9.0
[pip3] mypy-extensions==1.0.0
[pip3] numpy==1.24.1
[pip3] nvidia-cublas-cu12==12.4.5.8
[pip3] nvidia-cuda-cupti-cu12==12.4.127
[pip3] nvidia-cuda-nvrtc-cu12==12.4.127
[pip3] nvidia-cuda-runtime-cu12==12.4.127
[pip3] nvidia-cudnn-cu12==9.1.0.70
[pip3] nvidia-cufft-cu12==11.2.1.3
[pip3] nvidia-curand-cu12==10.3.5.147
[pip3] nvidia-cusolver-cu12==11.6.1.9
[pip3] nvidia-cusparse-cu12==12.3.1.170
[pip3] nvidia-cusparselt-cu12==0.6.2
[pip3] nvidia-nccl-cu12==2.21.5
[pip3] nvidia-nvjitlink-cu12==12.4.127
[pip3] nvidia-nvtx-cu12==12.4.127
[pip3]
[pip3]
[pip3]
[pip3] optree==0.13.0
[pip3] torch==2.6.0
[pip3] torchaudio==2.7.0
[pip3] torchvision==0.21.0
[pip3] triton==3.2.0
[conda] ai-edge-torch 0.3.0 dev_0 <develop>
[conda] blas 1.0 mkl
[conda] cuda-cudart 12.1.105 0 nvidia
[conda] cuda-cupti 12.1.105 0 nvidia
[conda] cuda-libraries 12.1.0 0 nvidia
[conda] cuda-nvrtc 12.1.105 0 nvidia
[conda] cuda-nvtx 12.1.105 0 nvidia
[conda] cuda-opencl 12.4.127 0 nvidia
[conda] cuda-runtime 12.1.0 0 nvidia
[conda] ffmpeg 4.3 hf484d3e_0 pytorch
[conda] libcublas 12.1.0.26 0 nvidia
[conda] libcufft 11.0.2.4 0 nvidia
[conda] libcurand 10.3.5.147 0 nvidia
[conda] libcusolver 11.4.4.55 0 nvidia
[conda] libcusparse 12.0.2.55 0 nvidia
[conda] libjpeg-turbo 2.0.0 h9bf148f_0 pytorch
[conda] libnvjitlink 12.1.105 0 nvidia
[conda] mkl 2023.1.0 h213fc3f_46344
[conda] mkl-service 2.4.0 py310h5eee18b_1
[conda] mkl_fft 1.3.8 py310h5eee18b_0
[conda] mkl_random 1.2.4 py310hdb19cb5_0
[conda] numpy 1.24.1 pypi_0 pypi
[conda] nvidia-cublas-cu12 12.4.5.8 pypi_0 pypi
[conda] nvidia-cuda-cupti-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-cuda-nvrtc-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-cuda-runtime-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-cudnn-cu12 9.1.0.70 pypi_0 pypi
[conda] nvidia-cufft-cu12 11.2.1.3 pypi_0 pypi
[conda] nvidia-curand-cu12 10.3.5.147 pypi_0 pypi
[conda] nvidia-cusolver-cu12 11.6.1.9 pypi_0 pypi
[conda] nvidia-cusparse-cu12 12.3.1.170 pypi_0 pypi
[conda] nvidia-cusparselt-cu12 0.6.2 pypi_0 pypi
[conda] nvidia-nccl-cu12 2.21.5 pypi_0 pypi
[conda] nvidia-nvjitlink-cu12 12.4.127 pypi_0 pypi
[conda] nvidia-nvtx-cu12 12.4.127 pypi_0 pypi
[conda] optree 0.13.0 pypi_0 pypi
[conda] pytorch-cuda 12.1 ha16c6d3_5 pytorch
[conda] pytorch-mutex 1.0 cuda pytorch
[conda] torch 2.6.0 pypi_0 pypi
[conda] torchaudio 2.7.0 pypi_0 pypi
[conda] torchfix 0.1.1 pypi_0 pypi
[conda] torchvision 0.21.0 pypi_0 pypi
[conda] triton 3.2.0 pypi_0 pypi
cc @ezyang @gchanan @zou3519 @kadeng @msaroufim @chauhang @penguinwu @avikchaudhuri @gmagogsfm @zhxchen17 @tugsbayasgalan @angelayi @suo @ydwu4