Issue Station
Sign In
Tools hereToolbox

pytorch - 💡(How to fix) Fix [CUDA] illegal memory read on fmha_cutlassF_f32_aligned_64x64_rf_sm80

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…

Fix Action

Fix / Workaround

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): 104 On-line CPU(s) list: 0-103 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Gold 5320 CPU @ 2.20GHz CPU family: 6 Model: 106 Thread(s) per core: 2 Core(s) per socket: 26 Socket(s): 2 Stepping: 6 CPU max MHz: 3400.0000 CPU min MHz: 800.0000 BogoMIPS: 4400.00 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 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 invpcid_single 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 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 2.4 MiB (52 instances) L1i cache: 1.6 MiB (52 instances) L2 cache: 65 MiB (52 instances) L3 cache: 78 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-25,52-77 NUMA node1 CPU(s): 26-51,78-103 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Indirect target selection: Mitigation; Aligned branch/return thunks Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable 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; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop Vulnerability Srbds: Not affected Vulnerability Tsa: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Not affected

Code Example

import torch
print("torch:", torch.__version__)

torch.cuda.init()
gpu = torch.device('cuda')

B, H, S, D = 6, 4, 64, 64
storage = torch.zeros(B * H * S * D + 4, dtype=torch.float32, device=gpu)
q = storage[1:1 + B * H * S * D].view(B, H, S, D)
k = storage[2:2 + B * H * S * D].view(B, H, S, D)
v = storage[3:3 + B * H * S * D].view(B, H, S, D)

with torch.nn.attention.sdpa_kernel([torch.nn.attention.SDPBackend.EFFICIENT_ATTENTION]):
    out = torch.nn.functional.scaled_dot_product_attention(q, k, v)
torch.cuda.synchronize()

---

========= COMPUTE-SANITIZER
========= Invalid __global__ read of size 16 bytes
=========     at fmha_cutlassF_f32_aligned_64x64_rf_sm80(PyTorchMemEffAttention::AttentionKernel<float, cutlass::arch::Sm80, (bool)1, (int)64, (int)64, (int)64, (bool)1, (bool)1>::Params)+0x2450
=========     by thread (0,2,0) in block (0,0,0)
=========     Address 0x7fe6e5e02004 is misaligned
RAW_BUFFERClick to expand / collapse

🐛 Describe the bug

import torch
print("torch:", torch.__version__)

torch.cuda.init()
gpu = torch.device('cuda')

B, H, S, D = 6, 4, 64, 64
storage = torch.zeros(B * H * S * D + 4, dtype=torch.float32, device=gpu)
q = storage[1:1 + B * H * S * D].view(B, H, S, D)
k = storage[2:2 + B * H * S * D].view(B, H, S, D)
v = storage[3:3 + B * H * S * D].view(B, H, S, D)

with torch.nn.attention.sdpa_kernel([torch.nn.attention.SDPBackend.EFFICIENT_ATTENTION]):
    out = torch.nn.functional.scaled_dot_product_attention(q, k, v)
torch.cuda.synchronize()
========= COMPUTE-SANITIZER
========= Invalid __global__ read of size 16 bytes
=========     at fmha_cutlassF_f32_aligned_64x64_rf_sm80(PyTorchMemEffAttention::AttentionKernel<float, cutlass::arch::Sm80, (bool)1, (int)64, (int)64, (int)64, (bool)1, (bool)1>::Params)+0x2450
=========     by thread (0,2,0) in block (0,0,0)
=========     Address 0x7fe6e5e02004 is misaligned

SDPA CUDA path appears to select an aligned CUTLASS kernel based on stride/head-dimension checks, but it does not also check whether the actual Q/K/V data pointers are 16-byte aligned when tensors have nonzero storage offsets.

Versions

Collecting environment information... PyTorch version: 2.11.0+cu128 Is debug build: False CUDA used to build PyTorch: 12.8 ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.2 LTS (x86_64) GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04.3) 11.4.0 Clang version: 14.0.0-1ubuntu1.1 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-5.15.0-174-generic-x86_64-with-glibc2.35 Is CUDA available: True CUDA runtime version: 11.5.119 CUDA_MODULE_LOADING set to: GPU models and configuration: GPU 0: NVIDIA A30 GPU 1: NVIDIA A30

Nvidia driver version: 560.28.03 cuDNN version: Probably one of the following: /usr/lib/x86_64-linux-gnu/libcudnn.so.8.9.7 /usr/lib/x86_64-linux-gnu/libcudnn.so.9.3.0 /usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.3.0 /usr/lib/x86_64-linux-gnu/libcudnn_adv_infer.so.8.9.7 /usr/lib/x86_64-linux-gnu/libcudnn_adv_train.so.8.9.7 /usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.3.0 /usr/lib/x86_64-linux-gnu/libcudnn_cnn_infer.so.8.9.7 /usr/lib/x86_64-linux-gnu/libcudnn_cnn_train.so.8.9.7 /usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.3.0 /usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.3.0 /usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.3.0 /usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.3.0 /usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.3.0 /usr/lib/x86_64-linux-gnu/libcudnn_ops_infer.so.8.9.7 /usr/lib/x86_64-linux-gnu/libcudnn_ops_train.so.8.9.7 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: 46 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 104 On-line CPU(s) list: 0-103 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Gold 5320 CPU @ 2.20GHz CPU family: 6 Model: 106 Thread(s) per core: 2 Core(s) per socket: 26 Socket(s): 2 Stepping: 6 CPU max MHz: 3400.0000 CPU min MHz: 800.0000 BogoMIPS: 4400.00 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 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 invpcid_single 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 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid fsrm md_clear pconfig flush_l1d arch_capabilities Virtualization: VT-x L1d cache: 2.4 MiB (52 instances) L1i cache: 1.6 MiB (52 instances) L2 cache: 65 MiB (52 instances) L3 cache: 78 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0-25,52-77 NUMA node1 CPU(s): 26-51,78-103 Vulnerability Gather data sampling: Mitigation; Microcode Vulnerability Indirect target selection: Mitigation; Aligned branch/return thunks Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Mitigation; Clear CPU buffers; SMT vulnerable 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; PBRSB-eIBRS SW sequence; BHI SW loop, KVM SW loop Vulnerability Srbds: Not affected Vulnerability Tsa: Not affected Vulnerability Tsx async abort: Not affected Vulnerability Vmscape: Not affected

Versions of relevant libraries: [pip3] numpy==2.2.6 [pip3] nvidia-cublas-cu12==12.8.4.1 [pip3] nvidia-cuda-cupti-cu12==12.8.90 [pip3] nvidia-cuda-nvrtc-cu12==12.8.93 [pip3] nvidia-cuda-runtime-cu12==12.8.90 [pip3] nvidia-cudnn-cu12==9.19.0.56 [pip3] nvidia-cufft-cu12==11.3.3.83 [pip3] nvidia-curand-cu12==10.3.9.90 [pip3] nvidia-cusolver-cu12==11.7.3.90 [pip3] nvidia-cusparse-cu12==12.5.8.93 [pip3] nvidia-cusparselt-cu12==0.7.1 [pip3] nvidia-nccl-cu12==2.28.9 [pip3] nvidia-nvjitlink-cu12==12.8.93 [pip3] nvidia-nvtx-cu12==12.8.90 [pip3] torch==2.11.0+cu128 [pip3] triton==3.6.0 [conda] _anaconda_depends 2023.09 py311_mkl_1
[conda] blas 1.0 mkl
[conda] intel-openmp 2023.1.0 hdb19cb5_46306
[conda] magma-cuda121 2.6.1 1 pytorch [conda] mkl 2023.1.0 h213fc3f_46344
[conda] mkl-include 2023.2.0 intel_49495 intel [conda] mkl-service 2.4.0 py311h5eee18b_1
[conda] mkl-static 2023.2.0 intel_49495 intel [conda] mkl_fft 1.3.8 py311h5eee18b_0
[conda] mkl_random 1.2.4 py311hdb19cb5_0
[conda] numpy 1.26.4 py311h08b1b3b_0
[conda] numpy-base 1.26.4 py311hf175353_0
[conda] numpydoc 1.5.0 py311h06a4308_0
[conda] optree 0.10.0 pypi_0 pypi [conda] pytorch-triton 3.0.0+989adb9a29 pypi_0 pypi [conda] tbb 2021.8.0 hdb19cb5_0
[conda] tbb4py 2021.8.0 py311hdb19cb5_0
[conda] torch 2.3.0a0+git443444d dev_0 <develop>

cc @ptrblck @msaroufim @eqy @jerryzh168 @tinglvv @nWEIdia @drisspg @liangel-02 @howardzhang-cv

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#batch processing#GPU compatibility#latency issue#model loading

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 [CUDA] illegal memory read on fmha_cutlassF_f32_aligned_64x64_rf_sm80