Unable to run LAMMPS with deepmd and voronoi package using trained model

[syue7979]

Bug summary

We tried to run LAMMPS with deepmd+voronoi, it leads to the error:

ERROR: Unrecognized pair style 'deepmd' (src/force.cpp:275)
Last command: pair_style deepmd Ti5_small_i2_compressed_step01.pb
Cuda driver error 4 in call at file '/opt/lammps/lib/gpu/geryon/nvd_device.h' in line 429.
Cuda driver error 4 in call at file '/opt/lammps/lib/gpu/geryon/nvd_device.h' in line 430.

Has anyone ever encountered this error? Thanks in advance.

DeePMD-kit Version

deepmd−kit=2.2.7

TensorFlow Version

TensorFlow2.9.0

How did you download the software?

conda

Input Files, Running Commands, Error Log, etc.

Input file

#INITIALIZATION
clear
units            metal
dimension        3
boundary         p p p
atom_style       atomic
atom_modify      map array
variable srate   equal -0.001 # in s^-1

#ATOM DEFINITION
read_data 	 PureAlpha.lmp
pair_style deepmd Ti5_small_i2_compressed_step01.pb
pair_coeff * *      
neighbor 2.0 bin
neigh_modify delay 10 check yes
timestep	 0.001

#RELAXATION
reset_timestep   0
velocity all 	 create 100.0 12345 mom yes rot no dist gaussian
fix    1 all     npt temp 100.0 100.0 1.0 aniso 0.0 0.0 10.0  
thermo 100

run 10000
unfix 1
variable tmp equal "ly"
variable L0 equal ${tmp}
print "Initial Length, Ly = ${L0}"

## Strain
reset_timestep 0
fix 2 all nph x 0.0 0.0 10.0 z 0.0 0.0 10.0
variable srate1 equal "-v_srate / 1.0e12"
fix 3 all deform 1 y erate ${srate1} units box remap x

variable strain equal "(ly - v_L0)/v_L0"
variable vs equal "v_strain"
variable px equal "-pxx/10000"
variable py equal "-pyy/10000"
variable pz equal "-pzz/10000"
fix data1 all print 100 "${vs} ${px} ${py} ${pz} " file Strain-Stress.txt screen no

## Per-Stress
compute PerStress all centroid/stress/atom NULL
# Per-Volume
compute v all voronoi/atom
variable PerStressX atom c_PerStress[1]/c_v[1]/10000
variable PerStressY atom c_PerStress[2]/c_v[1]/10000
variable PerStressZ atom c_PerStress[3]/c_v[1]/10000
#c_v[1] is the volume of single atom, c_[2] is Number of faces of atomic polyhedron.

## PotEng
compute peratom all pe/atom
compute 1 all reduce sum c_peratom

dump 1 all custom 100 Alpha.lmc id xs ys zs c_v[1] v_PerStressX v_PerStressY v_PerStressZ c_peratom
dump_modify 1 sort id
thermo 100
thermo_style custom step pe c_1 temp v_px v_py v_pz ke press
run 10000

Running Commands

lmp -sf gpu -in AllPureAlpha.in

Error log

ERROR: Unrecognized pair style 'deepmd' (src/force.cpp:275)
Last command: pair_style deepmd Ti5_small_i2_compressed_step01.pb
Cuda driver error 4 in call at file '/opt/lammps/lib/gpu/geryon/nvd_device.h' in line 429.
Cuda driver error 4 in call at file '/opt/lammps/lib/gpu/geryon/nvd_device.h' in line 430.

Steps to Reproduce

PureAlpha.lmp.zip

Further Information, Files, and Links

No response

[njzjz]

#1809

[njzjz]

Close, as no more information is given to reproduce the issue.