Files
Lize CaiandGitHub fab85e09c2 update fluid kserve sample to use huggingface servingruntime (#3907)
* update fluid kserve demo to use huggingface servingruntime and other model.

Signed-off-by: Lize Cai <[email protected]>

* fix lint

Signed-off-by: Lize Cai <[email protected]>

* explicitly set custom servingruntime, update devshm.

Signed-off-by: Lize Cai <[email protected]>

* update the args in custom kserve hfserver

Signed-off-by: Lize Cai <[email protected]>

* address comments

Signed-off-by: Lize Cai <[email protected]>

* add return of line

Signed-off-by: Lize Cai <[email protected]>

---------

Signed-off-by: Lize Cai <[email protected]>
2024-09-23 07:00:02 -04:00

68 lines
1.7 KiB
YAML

apiVersion: data.fluid.io/v1alpha1
kind: Dataset
metadata:
name: s3-data
spec:
mounts:
- mountPoint: "s3://${bucket}/models/meta-llama--Meta-Llama-3.1-8B-Instruct/"
name: llama-31-8b-instruct
options:
fs.s3.region: "eu-central-1"
fs.s3.endpoint: "s3.eu-central-1.amazonaws.com"
encryptOptions:
- name: fs.s3.accessKeyId
valueFrom:
secretKeyRef:
name: s3creds
key: AWS_ACCESS_KEY_ID
- name: fs.s3.accessKeySecret
valueFrom:
secretKeyRef:
name: s3creds
key: AWS_SECRET_ACCESS_KEY
accessModes:
- ReadOnlyMany
nodeAffinity:
required:
nodeSelectorTerms:
- matchExpressions:
- key: node.kubernetes.io/instance-type
operator: In
values:
- "m5n.xlarge"
placement: "Shared"
---
apiVersion: data.fluid.io/v1alpha1
kind: JindoRuntime
metadata:
name: s3-data
spec:
replicas: 3
tieredstore:
levels:
- mediumtype: SSD
path: /mnt/ssd0/cache
quota: 100Gi
high: "0.95"
low: "0.7"
master:
nodeSelector:
node.kubernetes.io/instance-type: m5n.xlarge
worker:
nodeSelector:
node.kubernetes.io/instance-type: m5n.xlarge
fuse:
properties:
fs.jindofsx.data.cache.enable: "true"
# performance optimization
fs.jindofsx.stream.maxPendingBlocks: "200"
fs.s3.download.queue.size: "16"
fs.s3.download.thread.concurrency: "32"
fs.s3.read.readahead.buffer.count: "16"
args:
- -okernel_cache
- -oro
- -oattr_timeout=7200
- -oentry_timeout=7200
- -ometrics_port=9089