Description
🐛 Describe the bug
Upgrading to PyTorch 2.7 makes the following script randomly hang in distributed mode:
import argparse
import os
import torch
def main(bad = False):
local_rank = int(os.environ["LOCAL_RANK"])
device = torch.device("cuda", local_rank)
torch.cuda.set_device(device)
if bad:
torch.distributed.init_process_group("nccl", device_id=device)
else:
torch.distributed.init_process_group("nccl")
device = torch.device("cuda")
rank = torch.distributed.get_rank()
for i in range(10000):
if rank == 0:
if i % 10 == 0:
print(i)
a = torch.ones(3, device=device)
else:
a = torch.zeros(3, device=device)
torch.distributed.broadcast(a, src=0)
torch.distributed.destroy_process_group()
if __name__ == "__main__":
parser = argparse.ArgumentParser()
parser.add_argument("--bad", action="store_true", help="Shows the bug")
args = parser.parse_args()
main(args.bad)More precisely torchrun --nproc_per_node 8 -- script.py --bad will randomly start hanging (you might need to launch it a couple of times) whereas torchrun --nproc_per_node 8 -- script.py is fine.
torchrun --nproc_per_node 8 -- script.py --bad completes normally in 2.6.0, so this looks like a regression in PyTorch 2.7. We tried different kinds of GPUs and it looks like the bug appears on all of them.
Versions
Collecting environment information...
PyTorch version: 2.7.0+cu126
Is debug build: False
CUDA used to build PyTorch: 12.6
ROCM used to build PyTorch: N/A
OS: Rocky Linux release 8.10 (Green Obsidian) (x86_64)
GCC version: (GCC) 8.5.0 20210514 (Red Hat 8.5.0-26)
Clang version: 18.1.8 (Red Hat 18.1.8-1.module+el8.10.0+1875+4f0b06db)
CMake version: version 3.26.5
Libc version: glibc-2.28
Python version: 3.10.17 (main, Apr 9 2025, 10:09:40) [GCC 8.5.0 20210514 (Red Hat 8.5.0-24)] (64-bit runtime)
Python platform: Linux-6.1.134-1.el8.jane3.x86_64-x86_64-with-glibc2.28
Is CUDA available: True
CUDA runtime version: Could not collect
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration:
GPU 0: NVIDIA H100 80GB HBM3
GPU 1: NVIDIA H100 80GB HBM3
GPU 2: NVIDIA H100 80GB HBM3
GPU 3: NVIDIA H100 80GB HBM3
GPU 4: NVIDIA H100 80GB HBM3
GPU 5: NVIDIA H100 80GB HBM3
GPU 6: NVIDIA H100 80GB HBM3
GPU 7: NVIDIA H100 80GB HBM3
Nvidia driver version: 570.133.20
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
CPU(s): 112
On-line CPU(s) list: 0-111
Thread(s) per core: 1
Core(s) per socket: 56
Socket(s): 2
NUMA node(s): 2
Vendor ID: GenuineIntel
CPU family: 6
Model: 143
Model name: Intel(R) Xeon(R) Platinum 8480+
Stepping: 8
CPU MHz: 800.000
CPU max MHz: 3800.0000
CPU min MHz: 800.0000
BogoMIPS: 4000.00
L1d cache: 48K
L1i cache: 32K
L2 cache: 2048K
L3 cache: 107520K
NUMA node0 CPU(s): 0-55
NUMA node1 CPU(s): 56-111
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 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 cat_l2 cdp_l3 invpcid_single cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced 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 avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts hwp hwp_act_window hwp_epp hwp_pkg_req avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities
Versions of relevant libraries:
[pip3] numpy==2.2.6
[pip3] nvidia-cublas-cu12==12.6.4.1
[pip3] nvidia-cuda-cupti-cu12==12.6.80
[pip3] nvidia-cuda-nvrtc-cu12==12.6.77
[pip3] nvidia-cuda-runtime-cu12==12.6.77
[pip3] nvidia-cudnn-cu12==9.5.1.17
[pip3] nvidia-cufft-cu12==11.3.0.4
[pip3] nvidia-curand-cu12==10.3.7.77
[pip3] nvidia-cusolver-cu12==11.7.1.2
[pip3] nvidia-cusparse-cu12==12.5.4.2
[pip3] nvidia-cusparselt-cu12==0.6.3
[pip3] nvidia-nccl-cu12==2.26.2
[pip3] nvidia-nvjitlink-cu12==12.6.85
[pip3] nvidia-nvtx-cu12==12.6.77
[pip3] torch==2.7.0
[pip3] triton==3.3.0
[conda] Could not collect
cc @ezyang @gchanan @zou3519 @kadeng @msaroufim @H-Huang @awgu @wanchaol @fegin @fduwjj @wz337 @wconstab @d4l3k