Files
ecb211047f Model cache controller and node agent (#4089)
* LocalModelNode Daemonset Controller Skeleton (#4026)

* hello world controller

Signed-off-by: Gavin Li <[email protected]>

* go fmt

Signed-off-by: Gavin Li <[email protected]>

* daemonset

Signed-off-by: Gavin Li <[email protected]>

* Update Makefile

Co-authored-by: Jin Dong <[email protected]>
Signed-off-by: Gavin Li <[email protected]>

* make generate

Signed-off-by: Gavin Li <[email protected]>

* install LocalModelNode CRD

Signed-off-by: Gavin Li <[email protected]>

* feedback

Signed-off-by: Gavin Li <[email protected]>

* make manifests

Signed-off-by: Gavin Li <[email protected]>

* agent

Signed-off-by: Gavin Li <[email protected]>

Co-authored-by: Jin Dong <[email protected]>

* LocalModelController creates LocalModelNode resource for ready nodes (#4036)

* Manage localmodelNode

Signed-off-by: Jin Dong <[email protected]>

* Update patch

Signed-off-by: Jin Dong <[email protected]>

* Fix rbac

Signed-off-by: Jin Dong <[email protected]>

* Add a test to controller_test.go

Signed-off-by: Jin Dong <[email protected]>

* Update pkg/controller/v1alpha1/localmodel/controller.go

Co-authored-by: Dan Sun <[email protected]>
Signed-off-by: Jin Dong <[email protected]>

---------

Signed-off-by: Jin Dong <[email protected]>
Co-authored-by: Dan Sun <[email protected]>

* Delete from LocalModelNode when the localmodel is deleted (#4053)

* Delete model from LocalModelNode

Signed-off-by: Jin Dong <[email protected]>

* Cleanup code

Signed-off-by: Jin Dong <[email protected]>

* Cleanup code

Signed-off-by: Jin Dong <[email protected]>

* Fix lint

Signed-off-by: Jin Dong <[email protected]>

* Initializer node status map

Signed-off-by: Jin Dong <[email protected]>

* Address comments

Signed-off-by: Jin Dong <[email protected]>

---------

Signed-off-by: Jin Dong <[email protected]>

* Update Model status from LocalModelNode status (#4056)

* Delete model from LocalModelNode

Signed-off-by: Jin Dong <[email protected]>

* Cleanup code

Signed-off-by: Jin Dong <[email protected]>

* Cleanup code

Signed-off-by: Jin Dong <[email protected]>

* Fix lint

Signed-off-by: Jin Dong <[email protected]>

* Initializer node status map

Signed-off-by: Jin Dong <[email protected]>

* Update status

Signed-off-by: Jin Dong <[email protected]>

* Update localmodel node status

Signed-off-by: Jin Dong <[email protected]>

* Remove job dependency from localmodel controller

Signed-off-by: Jin Dong <[email protected]>

* Remove some unused lines

Signed-off-by: Jin Dong <[email protected]>

* Add comments

Signed-off-by: Jin Dong <[email protected]>

---------

Signed-off-by: Jin Dong <[email protected]>

* LocalModelNode Agent that creates download jobs and update statuses from jobs (#4075)

* download working

Signed-off-by: Gavin Li <[email protected]>

* delete working

Signed-off-by: Gavin Li <[email protected]>

* cleanup

Signed-off-by: Gavin Li <[email protected]>

* gofmt

Signed-off-by: Gavin Li <[email protected]>

* Delete model from LocalModelNode

Signed-off-by: Jin Dong <[email protected]>

* Cleanup code

Signed-off-by: Jin Dong <[email protected]>

* Fix lint

Signed-off-by: Jin Dong <[email protected]>

* Initializer node status map

Signed-off-by: Jin Dong <[email protected]>

* Update status

Signed-off-by: Jin Dong <[email protected]>

* Update localmodel node status

Signed-off-by: Jin Dong <[email protected]>

* Remove job dependency from localmodel controller

Signed-off-by: Jin Dong <[email protected]>

* Remove some unused lines

Signed-off-by: Jin Dong <[email protected]>

* Add comments

Signed-off-by: Jin Dong <[email protected]>

* Update manager

Signed-off-by: Jin Dong <[email protected]>

* Update rbac

Signed-off-by: Jin Dong <[email protected]>

* Add tests and temporarily remove delete models code

Signed-off-by: Jin Dong <[email protected]>

* Do not create download jobs if model is already downloaded

Signed-off-by: Jin Dong <[email protected]>

* remove mislieading log line

Signed-off-by: Jin Dong <[email protected]>

* Clean up code a little bit

Signed-off-by: Jin Dong <[email protected]>

* Update configurations

Signed-off-by: Jin Dong <[email protected]>

* update test

Signed-off-by: Jin Dong <[email protected]>

* Use a fixed name for the download container

Signed-off-by: Jin Dong <[email protected]>

---------

Signed-off-by: Gavin Li <[email protected]>
Signed-off-by: Jin Dong <[email protected]>
Co-authored-by: Gavin Li <[email protected]>

* Delete models from local disk when they are not in LocalModelNode spec (#4084)

* download working

Signed-off-by: Gavin Li <[email protected]>

* delete working

Signed-off-by: Gavin Li <[email protected]>

* Delete model from LocalModelNode

Signed-off-by: Jin Dong <[email protected]>

* Initializer node status map

Signed-off-by: Jin Dong <[email protected]>

* Update status

Signed-off-by: Jin Dong <[email protected]>

* Update localmodel node status

Signed-off-by: Jin Dong <[email protected]>

* Update manager

Signed-off-by: Jin Dong <[email protected]>

* Update rbac

Signed-off-by: Jin Dong <[email protected]>

* Add tests and temporarily remove delete models code

Signed-off-by: Jin Dong <[email protected]>

* Do not create download jobs if model is already downloaded

Signed-off-by: Jin Dong <[email protected]>

* Delete function

Signed-off-by: Jin Dong <[email protected]>

* Update configurations

Signed-off-by: Jin Dong <[email protected]>

* Add test and Fix deletion code

Signed-off-by: Jin Dong <[email protected]>

* Use a fixed name for the download container

Signed-off-by: Jin Dong <[email protected]>

* Remove deleted models from status and periodically trigger reconciliation

Signed-off-by: Jin Dong <[email protected]>

* Fix storagecontainer permissions and a minor change

Signed-off-by: Jin Dong <[email protected]>

---------

Signed-off-by: Gavin Li <[email protected]>
Signed-off-by: Jin Dong <[email protected]>
Co-authored-by: Gavin Li <[email protected]>

---------

Signed-off-by: Jin Dong <[email protected]>
Signed-off-by: Gavin Li <[email protected]>
Co-authored-by: Gavin Li <[email protected]>
Co-authored-by: Jin Dong <[email protected]>
2024-12-03 17:29:10 -05:00

12 lines
320 B
YAML

apiVersion: rbac.authorization.k8s.io/v1
kind: ClusterRoleBinding
metadata:
name: kserve-localmodelnode-agent-rolebinding
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: ClusterRole
name: kserve-localmodelnode-agent-role
subjects:
- kind: ServiceAccount
name: kserve-localmodelnode-agent
namespace: kserve