pytorch - 💡(How to fix) Fix [Inductor] ImportError: file too short when compiling model with nn.MultiheadAttention and invalid attn_mask shape

pytorch2026-04-20 12:28:41

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

Error Message

import torch import torch.nn as nn

class TestAttentionModel(nn.Module):

def __init__(self):
    super().__init__()
    self.fc1 = nn.Linear(20, 20)
    self.relu = nn.ReLU()
    self.fc2 = nn.Linear(20, 20)
    self.num_heads = 4
    self.attention = nn.MultiheadAttention(embed_dim=20, num_heads=1, batch_first=True)
    self.loss_fn = nn.MSELoss()

def my_attention(self, x, num_heads=1):
    attn_mask = torch.ones((x.shape[0], x.shape[1], x.shape[1]), dtype=torch.bool)
    return self.attention(x, x, x, attn_mask=attn_mask)

def forward(self, x):
    x = self.fc1(x)
    x = self.relu(x)
    x = self.fc2(x)
    (attn_out, _) = self.my_attention(x)
    return attn_out

def get_default_model(): return TestAttentionModel()

def get_sample_inputs(): x = torch.randn(2, 1, 20, requires_grad=True) return (x,)

def main(): model = get_default_model() model.eval() inputs = get_sample_inputs() try: with torch.no_grad(): output_eager = model(*inputs) print(f'Eager: {output_eager}') except Exception as e: print(f'Eager: {e}') try: compiled_model = torch.compile(model, fullgraph=True) with torch.no_grad(): output_compile = compiled_model(*inputs) print(f'Compile: {output_compile}') except Exception as e: print(f'\nOriginal exception:\n {e}') if name == 'main': main()

Fix Action

Fix / Workaround

Vulnerability Reg file data sampling: Mitigation; Clear Register File

Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl

Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization

Code Example

import torch
import torch.nn as nn

class TestAttentionModel(nn.Module):

    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(20, 20)
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(20, 20)
        self.num_heads = 4
        self.attention = nn.MultiheadAttention(embed_dim=20, num_heads=1, batch_first=True)
        self.loss_fn = nn.MSELoss()

    def my_attention(self, x, num_heads=1):
        attn_mask = torch.ones((x.shape[0], x.shape[1], x.shape[1]), dtype=torch.bool)
        return self.attention(x, x, x, attn_mask=attn_mask)

    def forward(self, x):
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        (attn_out, _) = self.my_attention(x)
        return attn_out

def get_default_model():
    return TestAttentionModel()

def get_sample_inputs():
    x = torch.randn(2, 1, 20, requires_grad=True)
    return (x,)

def main():
    model = get_default_model()
    model.eval()
    inputs = get_sample_inputs()
    try:
        with torch.no_grad():
            output_eager = model(*inputs)
        print(f'Eager: {output_eager}')
    except Exception as e:
        print(f'Eager: {e}')
    try:
        compiled_model = torch.compile(model, fullgraph=True)
        with torch.no_grad():
            output_compile = compiled_model(*inputs)
        print(f'Compile: {output_compile}')
    except Exception as e:
        print(f'\nOriginal exception:\n {e}')
if __name__ == '__main__':
    main()

---

Eager: tensor([[[nan, nan, ... nan]]]) 

Original exception:
 ImportError: /tmp/torchinductor_zuri/of/cofdmldnwkkwiz62obwkiilbxltifae24xzowvihzdl5juwvsw7x.main.so: file too short

RAW_BUFFERClick to expand / collapse

🐛 Describe the bug

When compiling a model that uses nn.MultiheadAttention with an incorrectly shaped attn_mask (created as (batch_size, seq_len, seq_len) instead of the expected (seq_len, seq_len) format), Inductor fails to compile and raises ImportError: file too short due to a corrupted .so file. The eager mode produces nan outputs but does not crash. code:

import torch
import torch.nn as nn

class TestAttentionModel(nn.Module):

    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(20, 20)
        self.relu = nn.ReLU()
        self.fc2 = nn.Linear(20, 20)
        self.num_heads = 4
        self.attention = nn.MultiheadAttention(embed_dim=20, num_heads=1, batch_first=True)
        self.loss_fn = nn.MSELoss()

    def my_attention(self, x, num_heads=1):
        attn_mask = torch.ones((x.shape[0], x.shape[1], x.shape[1]), dtype=torch.bool)
        return self.attention(x, x, x, attn_mask=attn_mask)

    def forward(self, x):
        x = self.fc1(x)
        x = self.relu(x)
        x = self.fc2(x)
        (attn_out, _) = self.my_attention(x)
        return attn_out

def get_default_model():
    return TestAttentionModel()

def get_sample_inputs():
    x = torch.randn(2, 1, 20, requires_grad=True)
    return (x,)

def main():
    model = get_default_model()
    model.eval()
    inputs = get_sample_inputs()
    try:
        with torch.no_grad():
            output_eager = model(*inputs)
        print(f'Eager: {output_eager}')
    except Exception as e:
        print(f'Eager: {e}')
    try:
        compiled_model = torch.compile(model, fullgraph=True)
        with torch.no_grad():
            output_compile = compiled_model(*inputs)
        print(f'Compile: {output_compile}')
    except Exception as e:
        print(f'\nOriginal exception:\n {e}')
if __name__ == '__main__':
    main()

output:

Eager: tensor([[[nan, nan, ... nan]]]) 

Original exception:
 ImportError: /tmp/torchinductor_zuri/of/cofdmldnwkkwiz62obwkiilbxltifae24xzowvihzdl5juwvsw7x.main.so: file too short

Versions

Environment Information PyTorch Build Details:

PyTorch version: 2.10.0.dev20251124+cpu

Is debug build: False

CUDA used to build PyTorch: Could not collect

ROCM used to build PyTorch: N/A

OS and Compilers:

OS: Ubuntu 24.04.1 LTS (x86_64)

GCC version: (Ubuntu 10.5.0-4ubuntu2) 10.5.0

Clang version: 18.1.3 (1)

CMake version: version 3.28.3

Libc version: glibc-2.39

Python Environment:

Python version: 3.12.3 (main, Nov 6 2025, 13:44:16) [GCC 13.3.0] (64-bit runtime)

Python platform: Linux-6.14.0-36-generic-x86_64-with-glibc2.39

Is CUDA available: False

CUDA runtime version: Could not collect

CUDA_MODULE_LOADING set to: N/A

GPU Information:

GPU models and configuration: GPU 0: NVIDIA GeForce RTX 4060 Laptop GPU

Nvidia driver version: 580.95.05

cuDNN version: Could not collect

Is XPU available: False

HIP runtime version: N/A

MIOpen runtime version: N/A

Is XNNPACK available: True

Caching allocator config: N/A

CPU Information:

Architecture: x86_64

CPU op-mode(s): 32-bit, 64-bit

Address sizes: 39 bits physical, 48 bits virtual

Byte Order: Little Endian

CPU(s): 32

On-line CPU(s) list: 0-31

Vendor ID: GenuineIntel

Model name: Intel(R) Core(TM) i9-14900HX

CPU family: 6

Model: 183

Thread(s) per core: 2

Core(s) per socket: 24

Socket(s): 1

Stepping: 1

CPU(s) scaling MHz: 33%

CPU max MHz: 5800.0000

CPU min MHz: 800.0000

BogoMIPS: 4838.40

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 est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb ssbd ibrs ibpb stibp ibrs_enhanced tpr_shadow flexpriority ept vpid ept_ad fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid rdseed adx smap clflushopt clwb intel_pt sha_ni xsaveopt xsavec xgetbv1 xsaves split_lock_detect user_shstk avx_vnni dtherm ida arat pln pts hwp hwp_notify hwp_act_window hwp_epp hwp_pkg_req hfi vnmi umip pku ospke waitpkg gfni vaes vpclmulqdq rdpid movdiri movdir64b fsrm md_clear serialize arch_lbr ibt flush_l1d arch_capabilities

Virtualization: VT-x

L1d cache: 896 KiB (24 instances)

L1i cache: 1.3 MiB (24 instances)

L2 cache: 32 MiB (12 instances)

L3 cache: 36 MiB (1 instance)

NUMA node(s): 1

NUMA node0 CPU(s): 0-31

Vulnerability Gather data sampling: Not affected

Vulnerability Ghostwrite: Not affected

Vulnerability Indirect target selection: 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: Mitigation; Clear Register File

Vulnerability Retbleed: Not affected

Vulnerability Spec rstack overflow: Not affected

Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl

Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization

Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS; IBPB conditional; PBRSB-eIBRS SW sequence; BHI BHI_DIS_S

Vulnerability Srbds: Not affected

Vulnerability Tsa: Not affected

Vulnerability Tsx async abort: Not affected

Vulnerability Vmscape: Mitigation; IBPB before exit to userspace

Versions of Relevant Libraries:

[pip3] numpy==2.3.3

[pip3] nvidia-cublas-cu12==12.1.3.1

[pip3] nvidia-cuda-cupti-cu12==12.1.105

[pip3] nvidia-cuda-nvrtc-cu12==12.1.105

[pip3] nvidia-cuda-runtime-cu12==12.1.105

[pip3] nvidia-cudnn-cu12==9.1.0.70

[pip3] nvidia-cufft-cu12==11.0.2.54

[pip3] nvidia-curand-cu12==10.3.2.106

[pip3] nvidia-cusolver-cu12==11.4.5.107

[pip3] nvidia-cusparse-cu12==12.1.0.106

[pip3] nvidia-nccl-cu12==2.21.5

[pip3] nvidia-nvjitlink-cu12==12.9.86

[pip3] nvidia-nvtx-cu12==12.1.105

[pip3] optree==0.18.0

[pip3] pytorch-triton-rocm==3.5.0

[pip3] torch==2.10.0.dev20251124+cpu

[pip3] torchao==0.15.0.dev20251124+cpu

[pip3] torchdata==0.12.0.dev20250909+cpu

[pip3] torchtext==0.17.0.dev20240912+cpu

[pip3] triton==3.1.0

[conda] Could not collect

cc @albanD @mruberry @jbschlosser @walterddr @mikaylagawarecki @chauhang @penguinwu @voznesenskym @EikanWang @jgong5 @Guobing-Chen @XiaobingSuper @zhuhaozhe @blzheng @wenzhe-nrv @jiayisunx @ipiszy @kadeng @muchulee8 @amjames @aakhundov @coconutruben @jataylo

extent analysis

TL;DR

The issue can be resolved by correcting the shape of the attn_mask in the my_attention method to match the expected format of (seq_len, seq_len).

Guidance

Verify the shape of attn_mask: Ensure that the attn_mask is created with the correct shape. In this case, it should be (seq_len, seq_len) instead of (batch_size, seq_len, seq_len).
Update the my_attention method: Modify the my_attention method to create the attn_mask with the correct shape.
Test the updated model: After updating the my_attention method, test the model again to ensure that it compiles and runs without errors.

Example

def my_attention(self, x, num_heads=1):
    seq_len = x.shape[1]
    attn_mask = torch.ones((seq_len, seq_len), dtype=torch.bool)
    return self.attention(x, x, x, attn_mask=attn_mask)

Notes

The provided code snippet and error message suggest that the issue is related to the shape of the attn_mask. However, without further information about the intended behavior of the model, it is difficult to provide a more detailed solution.

Recommendation

Apply the workaround by updating the my_attention method to create the attn_mask with the correct shape, as shown in the example above. This should resolve the issue and allow the model to compile and run without errors.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #prompt template #agent execution #callback error #memory management

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Data

Security

Network

Code

UI/UX

Text

System

Multimedia

Protocol

API

Engineering

pytorch - 💡(How to fix) Fix [Inductor] ImportError: file too short when compiling model with nn.MultiheadAttention and invalid attn_mask shape

Recommended Tools

GitHub issue graph ai analysis

Error Message

Fix Action

Fix / Workaround

Code Example

🐛 Describe the bug

Versions

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

TRENDING

pytorch - 💡(How to fix) Fix [Inductor] ImportError: file too short when compiling model with nn.MultiheadAttention and invalid attn_mask shape

Recommended Tools

GitHub issue graph ai analysis

Error Message

Fix Action

Fix / Workaround

Code Example

🐛 Describe the bug

Versions

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING