mirror of
https://github.com/hanzo-ml/trainer.git
synced 2026-09-24 00:31:34 +00:00
Tariq HasanandGitHub
1f57df4484
* ci(boilerplate): enforce copyright headers on YAML files Signed-off-by: tariq-hasan <[email protected]> * ci(boilerplate): enforce year-less header for new files Signed-off-by: tariq-hasan <[email protected]> --------- Signed-off-by: tariq-hasan <[email protected]>
41 lines
1.5 KiB
YAML
41 lines
1.5 KiB
YAML
# Copyright The Kubeflow Authors.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
|
|
# This example deploys the LAMMPS Molecular Dynamic Simulator
|
|
# with MPI orchestrated by the Flux workload manager on 4 nodes.
|
|
# This is "interactive" mode, so you can shell in to execute lmp.
|
|
# See lammps-train-job.yaml for more details on the setup, and
|
|
# instructions below for running lammps.
|
|
apiVersion: trainer.kubeflow.org/v1alpha1
|
|
kind: TrainJob
|
|
metadata:
|
|
name: lammps-flux-interactive
|
|
spec:
|
|
# Reference the pre-defined runtime by name
|
|
runtimeRef:
|
|
name: flux-distributed
|
|
trainer:
|
|
numNodes: 4
|
|
image: ghcr.io/converged-computing/metric-lammps:latest
|
|
command: ["sleep", "infinity"]
|
|
# To run lammps, shell into the 0-0 pod:
|
|
# # Source environment
|
|
# . /mnt/flux/flux-view.sh
|
|
# # Connect to the running lead broker socket
|
|
# flux proxy $fluxsocket bash
|
|
# # See Flux resources!
|
|
# flux resource list
|
|
# Run lammps!
|
|
# flux run -N 4 -n 4 lmp -v x 2 -v y 2 -v z 2 -in in.reaxc.hns -nocite
|