import os
import torch
from torch.distributed._tensor import init_device_mesh, Shard, distribute_tensor

os.environ["RANK"] = "0"
os.environ["WORLD_SIZE"] = "1"
os.environ["MASTER_ADDR"] = "localhost"
os.environ["MASTER_PORT"] = "12312"
torch.distributed.init_process_group(backend="nccl", world_size=1)

mesh = init_device_mesh("cuda", (int(1),))
big_tensor = torch.randn(123, 88)
my_dtensor = distribute_tensor(big_tensor, mesh, [Shard(dim=0)])

torch._foreach_mul([my_dtensor], 2.0)  # ok
torch._foreach_mul_([my_dtensor], torch.tensor(2.0))  # ok
torch._foreach_mul([my_dtensor], torch.tensor(2.0))  # not ok
torch._foreach_div([my_dtensor], torch.tensor(2.0))  # same problem

[rank0]: Traceback (most recent call last):
[rank0]:   File "/mnt/clusterstorage/workspace/kevin/foreachdtensor.py", line 18, in <module>
[rank0]:     torch._foreach_mul([my_dtensor], torch.tensor(2.0))  # not ok
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/_compile.py", line 31, in inner
[rank0]:     return disable_fn(*args, **kwargs)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/eval_frame.py", line 600, in _fn
[rank0]:     return fn(*args, **kwargs)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/distributed/_tensor/api.py", line 309, in __torch_dispatch__
[rank0]:     return DTensor._op_dispatcher.dispatch(
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/distributed/_tensor/_dispatch.py", line 117, in dispatch
[rank0]:     self.sharding_propagator.propagate(op_info)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/distributed/_tensor/_sharding_prop.py", line 185, in propagate
[rank0]:     output_sharding = self.propagate_op_sharding(op_info.schema)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/distributed/_tensor/_sharding_prop.py", line 197, in propagate_op_sharding_non_cached
[rank0]:     out_tensor_meta = self._propagate_tensor_meta(op_schema)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/distributed/_tensor/_sharding_prop.py", line 109, in _propagate_tensor_meta
[rank0]:     fake_out = op_schema.op(*fake_args, **fake_kwargs)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/_ops.py", line 667, in __call__
[rank0]:     return self_._op(*args, **kwargs)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/_compile.py", line 31, in inner
[rank0]:     return disable_fn(*args, **kwargs)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/_dynamo/eval_frame.py", line 600, in _fn
[rank0]:     return fn(*args, **kwargs)
[rank0]:   File "/usr/local/lib/python3.10/dist-packages/torch/distributed/_tensor/api.py", line 309, in __torch_dispatch__
[rank0]:     return DTensor._op_dispatcher.dispatch(
... (it goes into a loop until the recursion limit is hit)

PyTorch version: 2.4.0
Is debug build: False
CUDA used to build PyTorch: 12.4
ROCM used to build PyTorch: N/A

OS: Ubuntu 22.04.4 LTS (x86_64)
GCC version: (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
Clang version: Could not collect
CMake version: version 3.30.1
Libc version: glibc-2.35

Python version: 3.10.12 (main, Mar 22 2024, 16:50:05) [GCC 11.4.0] (64-bit runtime)
Python platform: Linux-5.19.17-coreweave-x86_64-with-glibc2.35
Is CUDA available: True
CUDA runtime version: 12.4.131
CUDA_MODULE_LOADING set to: LAZY
GPU models and configuration: GPU 0: NVIDIA A40
Nvidia driver version: 535.177
cuDNN version: Probably one of the following:
/usr/lib/x86_64-linux-gnu/libcudnn.so.9.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_adv.so.9.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_cnn.so.9.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_precompiled.so.9.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_engines_runtime_compiled.so.9.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_graph.so.9.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_heuristic.so.9.1.0
/usr/lib/x86_64-linux-gnu/libcudnn_ops.so.9.1.0
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
Address sizes:                   48 bits physical, 48 bits virtual
Byte Order:                      Little Endian
CPU(s):                          96
On-line CPU(s) list:             0-95
Vendor ID:                       AuthenticAMD
Model name:                      AMD EPYC 7413 24-Core Processor
CPU family:                      25
Model:                           1
Thread(s) per core:              2
Core(s) per socket:              24
Socket(s):                       2
Stepping:                        1
Frequency boost:                 enabled
CPU max MHz:                     3630.8101
CPU min MHz:                     1500.0000
BogoMIPS:                        5299.89
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 nopl nonstop_tsc cpuid extd_apicid aperfmperf rapl pni pclmulqdq monitor ssse3 fma cx16 pcid sse4_1 sse4_2 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 invpcid_single hw_pstate ssbd mba ibrs ibpb stibp vmmcall fsgsbase bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a rdseed adx smap clflushopt clwb sha_ni xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local clzero irperf xsaveerptr rdpru wbnoinvd amd_ppin brs arat npt lbrv svm_lock nrip_save tsc_scale vmcb_clean flushbyasid decodeassists pausefilter pfthreshold v_vmsave_vmload vgif v_spec_ctrl umip pku ospke vaes vpclmulqdq rdpid overflow_recov succor smca fsrm
Virtualization:                  AMD-V
L1d cache:                       1.5 MiB (48 instances)
L1i cache:                       1.5 MiB (48 instances)
L2 cache:                        24 MiB (48 instances)
L3 cache:                        256 MiB (8 instances)
NUMA node(s):                    2
NUMA node0 CPU(s):               0-23,48-71
NUMA node1 CPU(s):               24-47,72-95
Vulnerability Itlb multihit:     Not affected
Vulnerability L1tf:              Not affected
Vulnerability Mds:               Not affected
Vulnerability Meltdown:          Not affected
Vulnerability Mmio stale data:   Not affected
Vulnerability Retbleed:          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; Retpolines, IBPB conditional, IBRS_FW, STIBP always-on, RSB filling, PBRSB-eIBRS Not affected
Vulnerability Srbds:             Not affected
Vulnerability Tsx async abort:   Not affected

Versions of relevant libraries:
[pip3] gpytorch==1.12
[pip3] numpy==1.24.4
[pip3] torch==2.4.0
[pip3] torchaudio==2.4.0
[pip3] torchvision==0.19.0
[pip3] triton==3.0.0
[conda] Could not collect