标题: lammps遇到卡死问题，求助。 [打印本页] 作者Author: 懒洋洋喜洋洋 时间: yesterday 17:08 标题: lammps遇到卡死问题，求助。 (allegro-pol) root@bohrium-428977-1415901:/personal/b6# ~/lammps/build/lmp -in in.equilibrate
LAMMPS (2 Aug 2023)
OMP_NUM_THREADS environment is not set. Defaulting to 1 thread. (src/comm.cpp:98)
using 1 OpenMP thread(s) per MPI task
Reading data file ...
orthogonal box = (0 0 0) to (11.898254 11.898254 12.912077)
1 by 1 by 1 MPI processor grid
reading atoms ...
135 atoms
read_data CPU = 0.003 seconds
Allegro is using input precision f and output precision d
Allegro: Loading model from BaTiO3-E0.nequip.pth
Allegro: Freezing TorchScript model...
Type mapping:
Allegro type | Allegro name | LAMMPS type | LAMMPS name
0 | Ba | 1 | Ba
1 | Ti | 3 | Ti
2 | O | 2 | O
compute allegro will evaluate the quantity polarization of length 3 (src/compute_allegro.cpp:73)
compute allegro will evaluate the quantity polarizability of length 9 (src/compute_allegro.cpp:73)
compute allegro/atom will evaluate the quantity born_charge of length 9 with newton 1 (src/compute_allegro.cpp:63)
Neighbor list info ...
update: every = 1 steps, delay = 0 steps, check = yes
max neighbors/atom: 2000, page size: 100000
master list distance cutoff = 8
ghost atom cutoff = 8
binsize = 4, bins = 3 3 4
1 neighbor lists, perpetual/occasional/extra = 1 0 0
(1) pair allegro, perpetual
attributes: full, newton on, ghost
pair build: full/bin/ghost
stencil: full/ghost/bin/3d
bin: standard
Setting up Verlet run ...
Unit style : metal
Current step : 0
Time step : 0.002
Per MPI rank memory allocation (min/avg/max) = 3.929 | 3.929 | 3.929 Mbytes
PotEng Fmax Fnorm S/CPU CPULeft
-100941.72 0.46333129 2.1087595 0 0 我又重新按照之前的文献工作进行，这里使用的pytorch是1.13版本（pip install torch==1.13.0+cu117 torchvision==0.14.0+cu117 torchaudio==0.13.0 --extra-index-url https://download.pytorch.org/whl/cu117）。进行到这一步骤又没有反映了，我查阅AI回答是由于这个问题PyTorch 内部的 autograd 引擎仍然可能启动自己的线程池（例如通过 Intel TBB 或内部的并行后端），这些线程与 LAMMPS 的主线程交互时可能产生死锁。有大佬遇见过类似的问题吗？急急急！！！
复现文献的工作为https://github.com/mir-group/allegro-pol/