Issue Station
Sign In
Tools hereToolbox

pytorch - 💡(How to fix) Fix Inductor generates UnboundLocalError (bufXX referenced before assignment) when compiling torch.func.grad with MultiheadAttention + LayerNorm [1 participants]

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…
GitHub stats
pytorch/pytorch#181006•Fetched 2026-04-22 07:43:04
View on GitHub
Comments
0
Participants
1
Timeline
41
Reactions
0
Author
jasminetrailjasminetrail
Participants
jasminetrailjasminetrail
Timeline (top)
mentioned ×18subscribed ×18labeled ×5

Error Message

UnboundLocalError: local variable 'buf18' referenced before assignment

Fix Action

Fix / Workaround

CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 384 On-line CPU(s) list: 0-383 Vendor ID: AuthenticAMD Model name: AMD EPYC 9684X 96-Core Processor CPU family: 25 Model: 17 Thread(s) per core: 2 Core(s) per socket: 96 Socket(s): 2 Stepping: 2 BogoMIPS: 5099.98 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin cppc amd_ibpb_ret arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid overflow_recov succor smca fsrm flush_l1d debug_swap ibpb_exit_to_user Virtualization: AMD-V L1d cache: 6 MiB (192 instances) L1i cache: 6 MiB (192 instances) L2 cache: 192 MiB (192 instances) L3 cache: 2.3 GiB (24 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-95,192-287 NUMA node1 CPU(s): 96-191,288-383 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: Mitigation; Safe RET 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; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Mitigation; IBPB before exit to userspace

Code Example

UnboundLocalError: local variable 'buf18' referenced before assignment

---

import torch
import torch.nn as nn
import torch.func as _torch_func

_m_mha = nn.MultiheadAttention(4, 1, batch_first=True).eval()
_m_linear = nn.Linear(4, 49)
_m_ln = nn.LayerNorm([49])

torch.manual_seed(0)
t = torch.randn([10, 6, 4])

def model(t):
    t1, _ = _m_mha(t, t, t)
    t2 = _m_linear(t1)
    t3 = _m_ln(t2)
    return t3.mean()

# Eager: works fine
out_eager = _torch_func.grad(model)(t)
assert torch.isfinite(out_eager).all()

# Compiled: crashes
out_compiled = torch.compile(_torch_func.grad(model))(t)
RAW_BUFFERClick to expand / collapse

🐛 Describe the bug

Compiling a function using torch.func.grad fails with:

UnboundLocalError: local variable 'buf18' referenced before assignment

when the model contains MultiheadAttention → Linear → LayerNorm.

Minimal repro:

import torch
import torch.nn as nn
import torch.func as _torch_func

_m_mha = nn.MultiheadAttention(4, 1, batch_first=True).eval()
_m_linear = nn.Linear(4, 49)
_m_ln = nn.LayerNorm([49])

torch.manual_seed(0)
t = torch.randn([10, 6, 4])

def model(t):
    t1, _ = _m_mha(t, t, t)
    t2 = _m_linear(t1)
    t3 = _m_ln(t2)
    return t3.mean()

# Eager: works fine
out_eager = _torch_func.grad(model)(t)
assert torch.isfinite(out_eager).all()

# Compiled: crashes
out_compiled = torch.compile(_torch_func.grad(model))(t)

Error logs

Traceback (most recent call last): File "/home/test/bugs/crash_2c9ad2b8.py", line 23, in <module> out_compiled = torch.compile(_torch_func.grad(model))(t) File "/home/test/.venv/lib/python3.10/site-packages/torch/_dynamo/eval_frame.py", line 1024, in compile_wrapper return fn(*args, **kwargs) File "/home/test/.venv/lib/python3.10/site-packages/torch/_functorch/apis.py", line 432, in wrapper def wrapper(*args: _P.args, **kwargs: _P.kwargs) -> tuple[Any, torch.Tensor]: File "/home/test/.venv/lib/python3.10/site-packages/torch/_dynamo/eval_frame.py", line 1263, in _fn return fn(*args, **kwargs) File "/home/test/.venv/lib/python3.10/site-packages/torch/_functorch/aot_autograd.py", line 1200, in forward return compiled_fn(full_args) File "/home/test/.venv/lib/python3.10/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 566, in runtime_wrapper all_outs = call_func_at_runtime_with_args( File "/home/test/.venv/lib/python3.10/site-packages/torch/_functorch/_aot_autograd/utils.py", line 138, in call_func_at_runtime_with_args out = normalize_as_list(f(args)) File "/home/test/.venv/lib/python3.10/site-packages/torch/_functorch/_aot_autograd/utils.py", line 105, in g return f(*args) File "/home/test/.venv/lib/python3.10/site-packages/torch/autograd/function.py", line 596, in apply return super().apply(*args, **kwargs) # type: ignore[misc] File "/home/test/.venv/lib/python3.10/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 2503, in forward fw_outs = call_func_at_runtime_with_args( File "/home/test/.venv/lib/python3.10/site-packages/torch/_functorch/_aot_autograd/utils.py", line 138, in call_func_at_runtime_with_args out = normalize_as_list(f(args)) File "/home/test/.venv/lib/python3.10/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 783, in wrapper return compiled_fn(runtime_args) File "/home/test/.venv/lib/python3.10/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 1011, in inner_fn outs = compiled_fn(args) File "/home/test/.venv/lib/python3.10/site-packages/torch/_inductor/output_code.py", line 656, in call return self.current_callable(inputs) File "/tmp/torchinductor_test/ma/cma7ybugpx6qlu6pjz2b25bdadoyvbhv4tqqf53xnkpfmxmzj72c.py", line 781, in call cpp_fused_add_as_strided_div_expand_native_layer_norm_native_layer_norm_backward_ones_like_3(buf11, primals_7, primals_8, buf12, buf13, buf15, buf16, buf18, buf39) UnboundLocalError: local variable 'buf18' referenced before assignment

Versions

Collecting environment information... PyTorch version: 2.11.0+cu130 Is debug build: False CUDA used to build PyTorch: 13.0 ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.5 LTS (x86_64) GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0 Clang version: 15.0.0 ([email protected]:llvm/llvm-project.git 4ba6a9c9f65bbc8bd06e3652cb20fd4dfc846137) CMake version: version 3.22.1 Libc version: glibc-2.35

Python version: 3.10.12 (main, Mar 3 2026, 11:56:32) [GCC 11.4.0] (64-bit runtime) Python platform: Linux-6.8.0-94-generic-x86_64-with-glibc2.35 Is CUDA available: False CUDA runtime version: No CUDA CUDA_MODULE_LOADING set to: N/A GPU models and configuration: No CUDA Nvidia driver version: No CUDA cuDNN version: No CUDA Is XPU available: False HIP runtime version: N/A MIOpen runtime version: N/A Is XNNPACK available: True Caching allocator config: N/A

CPU: Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 52 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 384 On-line CPU(s) list: 0-383 Vendor ID: AuthenticAMD Model name: AMD EPYC 9684X 96-Core Processor CPU family: 25 Model: 17 Thread(s) per core: 2 Core(s) per socket: 96 Socket(s): 2 Stepping: 2 BogoMIPS: 5099.98 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx mmxext fxsr_opt pdpe1gb rdtscp lm constant_tsc rep_good amd_lbr_v2 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx f16c rdrand lahf_lm cmp_legacy svm extapic cr8_legacy abm sse4a misalignsse 3dnowprefetch osvw ibs skinit wdt tce topoext perfctr_core perfctr_nb bpext perfctr_llc mwaitx cpb cat_l3 cdp_l3 hw_pstate ssbd mba perfmon_v2 ibrs ibpb stibp ibrs_enhanced vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local user_shstk avx512_bf16 clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin cppc amd_ibpb_ret arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold avic v_vmsave_vmload vgif x2avic v_spec_ctrl vnmi avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg avx512_vpopcntdq la57 rdpid overflow_recov succor smca fsrm flush_l1d debug_swap ibpb_exit_to_user Virtualization: AMD-V L1d cache: 6 MiB (192 instances) L1i cache: 6 MiB (192 instances) L2 cache: 192 MiB (192 instances) L3 cache: 2.3 GiB (24 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-95,192-287 NUMA node1 CPU(s): 96-191,288-383 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: Mitigation; Safe RET 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; STIBP always-on; RSB filling; PBRSB-eIBRS Not affected; BHI Not affected Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Mitigation; IBPB before exit to userspace

Versions of relevant libraries: [pip3] numpy==2.2.6 [pip3] nvidia-cublas==13.1.0.3 [pip3] nvidia-cuda-cupti==13.0.85 [pip3] nvidia-cuda-nvrtc==13.0.88 [pip3] nvidia-cuda-runtime==13.0.96 [pip3] nvidia-cudnn-cu13==9.19.0.56 [pip3] nvidia-cufft==12.0.0.61 [pip3] nvidia-curand==10.4.0.35 [pip3] nvidia-cusolver==12.0.4.66 [pip3] nvidia-cusparse==12.6.3.3 [pip3] nvidia-cusparselt-cu13==0.8.0 [pip3] nvidia-nccl-cu13==2.28.9 [pip3] nvidia-nvjitlink==13.0.88 [pip3] nvidia-nvtx==13.0.85 [pip3] torch==2.11.0 [pip3] triton==3.6.0 [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 is likely due to a bug in the PyTorch compilation process when using torch.compile and torch.func.grad together, and a potential workaround is to avoid using torch.compile or to update PyTorch to a version where this bug is fixed.

Guidance

  • The error message UnboundLocalError: local variable 'buf18' referenced before assignment suggests that there is an issue with the compilation process, specifically with the handling of local variables.
  • The fact that the code works in eager mode but fails in compiled mode suggests that the issue is related to the compilation process.
  • To mitigate this issue, you can try avoiding the use of torch.compile or updating PyTorch to a version where this bug is fixed, if available.
  • Additionally, you can try to simplify the model or the compilation process to see if the issue persists, which can help in identifying the root cause.

Example

No specific code example can be provided without modifying the original code, but you can try to remove the torch.compile call to see if the issue is resolved:

out_compiled = _torch_func.grad(model)(t)

Instead of:

out_compiled = torch.compile(_torch_func.grad(model))(t)

Notes

The provided information does not include the exact version of PyTorch where this bug is fixed, if available. Therefore, the suggested workaround is to avoid using torch.compile or to update PyTorch to the latest version available.

Recommendation

Apply workaround: Avoid using torch.compile until the bug is fixed in a future version of PyTorch.

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#model compatibility#GPU setup#container setup#orchestration issue

Still need to ship something?

×6

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

Back to top recommendations

TRENDING

pytorch - 💡(How to fix) Fix Inductor generates UnboundLocalError (bufXX referenced before assignment) when compiling torch.func.grad with MultiheadAttention + LayerNorm [1 participants]