Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[WIP] Codeflare and Ray for distributing fine tuning #50

Draft
wants to merge 6 commits into
base: master
Choose a base branch
from
+3,692 −0
Draft

[WIP] Codeflare and Ray for distributing fine tuning #50

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
6 commits
Select commit Hold shift + click to select a range
2ce1e71
Add ray experiments
Shreyanand May 25, 2023
f2b4f67
Add recent changes
Shreyanand Jul 13, 2023
fc61809
Merge branch 'master' of https://github.com/redhat-et/foundation-mode…
Shreyanand Jul 27, 2023
1bcaf5b
Add initial ray experiments
Shreyanand Aug 10, 2023
af7e217
Add initial ray experiments
Shreyanand Aug 10, 2023
fdbfae4
Add initial ray experiments
Shreyanand Aug 10, 2023
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
193 changes: 193 additions & 0 deletions notebooks/ray-experiments/finetuneflan.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,193 @@
apiVersion: mcad.ibm.com/v1beta1
kind: AppWrapper
metadata:
labels:
orderedinstance: m5.xlarge_g4dn.xlarge
name: finetuneflan
namespace: default
spec:
priority: 9
resources:
GenericItems:
- custompodresources:
- limits:
cpu: 2
memory: 8G
nvidia.com/gpu: 0
replicas: 1
requests:
cpu: 2
memory: 8G
nvidia.com/gpu: 0
- limits:
cpu: 2
memory: 8G
nvidia.com/gpu: 1
replicas: 2
requests:
cpu: 1
memory: 2G
nvidia.com/gpu: 1
generictemplate:
apiVersion: ray.io/v1alpha1
kind: RayCluster
metadata:
labels:
appwrapper.mcad.ibm.com: finetuneflan
controller-tools.k8s.io: '1.0'
name: finetuneflan
namespace: default
spec:
autoscalerOptions:
idleTimeoutSeconds: 60
imagePullPolicy: Always
resources:
limits:
cpu: 500m
memory: 512Mi
requests:
cpu: 500m
memory: 512Mi
upscalingMode: Default
enableInTreeAutoscaling: false
headGroupSpec:
rayStartParams:
block: 'true'
dashboard-host: 0.0.0.0
num-gpus: '0'
serviceType: ClusterIP
template:
spec:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: finetuneflan
operator: In
values:
- finetuneflan
containers:
- env:
- name: MY_POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
- name: RAY_USE_TLS
value: '0'
- name: RAY_TLS_SERVER_CERT
value: /home/ray/workspace/tls/server.crt
- name: RAY_TLS_SERVER_KEY
value: /home/ray/workspace/tls/server.key
- name: RAY_TLS_CA_CERT
value: /home/ray/workspace/tls/ca.crt
image: ghcr.io/foundation-model-stack/base:ray2.1.0-py38-gpu-pytorch1.12.0cu116-20221213-193103
imagePullPolicy: Always
lifecycle:
preStop:
exec:
command:
- /bin/sh
- -c
- ray stop
name: ray-head
ports:
- containerPort: 6379
name: gcs
- containerPort: 8265
name: dashboard
- containerPort: 10001
name: client
resources:
limits:
cpu: 2
memory: 8G
nvidia.com/gpu: 0
requests:
cpu: 2
memory: 8G
nvidia.com/gpu: 0
imagePullSecrets: []
rayVersion: 2.1.0
workerGroupSpecs:
- groupName: small-group-finetuneflan
maxReplicas: 2
minReplicas: 2
rayStartParams:
block: 'true'
num-gpus: '1'
replicas: 2
template:
metadata:
annotations:
key: value
labels:
key: value
spec:
affinity:
nodeAffinity:
requiredDuringSchedulingIgnoredDuringExecution:
nodeSelectorTerms:
- matchExpressions:
- key: finetuneflan
operator: In
values:
- finetuneflan
containers:
- env:
- name: MY_POD_IP
valueFrom:
fieldRef:
fieldPath: status.podIP
- name: RAY_USE_TLS
value: '0'
- name: RAY_TLS_SERVER_CERT
value: /home/ray/workspace/tls/server.crt
- name: RAY_TLS_SERVER_KEY
value: /home/ray/workspace/tls/server.key
- name: RAY_TLS_CA_CERT
value: /home/ray/workspace/tls/ca.crt
image: ghcr.io/foundation-model-stack/base:ray2.1.0-py38-gpu-pytorch1.12.0cu116-20221213-193103
lifecycle:
preStop:
exec:
command:
- /bin/sh
- -c
- ray stop
name: machine-learning
resources:
limits:
cpu: 2
memory: 8G
nvidia.com/gpu: 1
requests:
cpu: 1
memory: 2G
nvidia.com/gpu: 1
imagePullSecrets: []
initContainers:
- command:
- sh
- -c
- until nslookup $RAY_IP.$(cat /var/run/secrets/kubernetes.io/serviceaccount/namespace).svc.cluster.local;
do echo waiting for myservice; sleep 2; done
image: busybox:1.28
name: init-myservice
replicas: 1
- generictemplate:
apiVersion: route.openshift.io/v1
kind: Route
metadata:
labels:
odh-ray-cluster-service: finetuneflan-head-svc
name: ray-dashboard-finetuneflan
namespace: default
spec:
port:
targetPort: dashboard
to:
kind: Service
name: finetuneflan-head-svc
replica: 1
Items: []
Loading