Issue Station
Sign In
Tools hereToolbox

pytorch - 💡(How to fix) Fix [Inductor] RuntimeError: weakref to UntypedStorage when compiling transpose(-2, -1) under inference_mode

Official PRs (…)
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.

Helpful · Quick feedback

Loading…

Error Message

RuntimeError: <weakref at 0x72cdcb030450; to 'torch.storage.UntypedStorage' at 0x72cdcafea810>

While executing %result : [num_users=1] = call_method[target=transpose](args = (%k, -2, -1), kwargs = {}) Original traceback: File "mini.py", line 16, in forward result = k.transpose(-2, -1)

torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised: RuntimeError: <weakref at 0x72cdcb030450; to 'torch.storage.UntypedStorage' at 0x72cdcafea810>

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 MinimalAttention(nn.Module):
    def __init__(self):
        super().__init__()
        self.head_dim = 64
    def forward(self, x):
        k = x.view(2, 20, 8, 64).transpose(1, 2)
        with torch.inference_mode():
            result = k.transpose(-2, -1)
        return result
model = MinimalAttention().eval()
x = torch.randn(2, 20, 512)
compiled_model = torch.compile(model, backend="inductor", fullgraph=True)
with torch.no_grad():
    output = compiled_model(x)

---

RuntimeError: <weakref at 0x72cdcb030450; to 'torch.storage.UntypedStorage' at 0x72cdcafea810>

While executing %result : [num_users=1] = call_method[target=transpose](args = (%k, -2, -1), kwargs = {})
Original traceback:
  File "mini.py", line 16, in forward
    result = k.transpose(-2, -1)

torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised:
RuntimeError: <weakref at 0x72cdcb030450; to 'torch.storage.UntypedStorage' at 0x72cdcafea810>
RAW_BUFFERClick to expand / collapse

🐛 Describe the bug

When compiling a model with torch.compile(backend="inductor", fullgraph=True), a RuntimeError related to weakref and UntypedStorage occurs. The error is triggered specifically when a transpose(-2, -1) operation on a 4D tensor is executed inside a torch.inference_mode() context. Eager mode runs successfully without any errors. code:

import torch
import torch.nn as nn
class MinimalAttention(nn.Module):
    def __init__(self):
        super().__init__()
        self.head_dim = 64
    def forward(self, x):
        k = x.view(2, 20, 8, 64).transpose(1, 2)
        with torch.inference_mode():
            result = k.transpose(-2, -1)
        return result
model = MinimalAttention().eval()
x = torch.randn(2, 20, 512)
compiled_model = torch.compile(model, backend="inductor", fullgraph=True)
with torch.no_grad():
    output = compiled_model(x)

output:

RuntimeError: <weakref at 0x72cdcb030450; to 'torch.storage.UntypedStorage' at 0x72cdcafea810>

While executing %result : [num_users=1] = call_method[target=transpose](args = (%k, -2, -1), kwargs = {})
Original traceback:
  File "mini.py", line 16, in forward
    result = k.transpose(-2, -1)

torch._dynamo.exc.BackendCompilerFailed: backend='inductor' raised:
RuntimeError: <weakref at 0x72cdcb030450; to 'torch.storage.UntypedStorage' at 0x72cdcafea810>

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 @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 avoiding the use of torch.inference_mode() or updating the PyTorch version to a more stable release.

Guidance

  • The error occurs when using torch.compile with the "inductor" backend and fullgraph=True, specifically when executing a transpose(-2, -1) operation inside torch.inference_mode().
  • Try removing the torch.inference_mode() context to see if the error persists.
  • Verify that the issue is not related to the specific PyTorch version (2.10.0.dev20251124+cpu) by testing with a stable release.
  • If the issue is specific to the "inductor" backend, try using a different backend or disabling fullgraph=True to isolate the problem.

Example

import torch
import torch.nn as nn

class MinimalAttention(nn.Module):
    def __init__(self):
        super().__init__()
        self.head_dim = 64

    def forward(self, x):
        k = x.view(2, 20, 8, 64).transpose(1, 2)
        # Remove torch.inference_mode() context
        result = k.transpose(-2, -1)
        return result

model = MinimalAttention().eval()
x = torch.randn(2, 20, 512)
compiled_model = torch.compile(model, backend="inductor", fullgraph=True)
with torch.no_grad():
    output = compiled_model(x)

Notes

The provided PyTorch version is a development build, which may contain unstable features or bugs. Updating to a stable release may resolve the issue.

Recommendation

Apply workaround: Remove torch.inference_mode() context or update PyTorch to a stable release, as the development build may contain bugs or unstable features.

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?
Loading…
#api#output truncation#response parsing#generation error#database connection

Still need to ship something?

×6

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

Back to top recommendations

TRENDING