Update Model status from LocalModelNode status #4056

greenmoon55 · 2024-11-15T21:59:11Z

What this PR does / why we need it:
This is built on top of #4053

Updates Model status from LocalModelNode status - this controller now watches LocalModelNode
Remove code and permissions for managing jobs

Which issue(s) this PR fixes (optional, in fixes #<issue number>(, fixes #<issue_number>, ...) format, will close the issue(s) when PR gets merged):
Fixes #

Type of changes
Please delete options that are not relevant.

Bug fix (non-breaking change which fixes an issue)
New feature (non-breaking change which adds functionality)
Breaking change (fix or feature that would cause existing functionality to not work as expected)
This change requires a documentation update

Feature/Issue validation/testing:

Please describe the tests that you ran to verify your changes and relevant result summary. Provide instructions so it can be reproduced.
Please also list any relevant details for your test configuration.

Test A
Test B
updated the tests
Logs

Special notes for your reviewer:

Please confirm that if this PR changes any image versions, then that's the sole change this PR makes.

Checklist:

Have you added unit/e2e tests that prove your fix is effective or that this feature works?
Has code been commented, particularly in hard-to-understand areas?
Have you made corresponding changes to the documentation?

Release note:

Re-running failed tests

/rerun-all - rerun all failed workflows.
/rerun-workflow <workflow name> - rerun a specific failed workflow. Only one workflow name can be specified. Multiple /rerun-workflow commands are allowed per comment.

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

yuzisun · 2024-11-19T06:22:57Z

@greenmoon55 Need to rebase the PR as #4053 is merged

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

yuzisun

/lgtm
/approve

* 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]>

* LocalModelNode Daemonset Controller Skeleton (kserve#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 (kserve#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 (kserve#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 (kserve#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 (kserve#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 (kserve#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]>

* LocalModelNode Daemonset Controller Skeleton (kserve#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 (kserve#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 (kserve#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 (kserve#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 (kserve#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 (kserve#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]> Signed-off-by: Dan Sun <[email protected]>

* Local Model Node CR (#3978) * init CR Signed-off-by: Gavin Li <[email protected]> * make generate Signed-off-by: Gavin Li <[email protected]> * make manifests Signed-off-by: Gavin Li <[email protected]> * black format Signed-off-by: Gavin Li <[email protected]> * fix generated python code Signed-off-by: Gavin Li <[email protected]> * feedback Signed-off-by: Gavin Li <[email protected]> * more feedback Signed-off-by: Gavin Li <[email protected]> * black format Signed-off-by: Gavin Li <[email protected]> * make manifests Signed-off-by: Gavin Li <[email protected]> --------- Signed-off-by: Gavin Li <[email protected]> Signed-off-by: Dan Sun <[email protected]> * 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]> Signed-off-by: Dan Sun <[email protected]> * Update ClusterLocalModel to LocalModelCache (#4105) * Update ClusterLocalModel to LocalModelCache Signed-off-by: Dan Sun <[email protected]> * Fix generation fmt Signed-off-by: Dan Sun <[email protected]> * black fmt Signed-off-by: Dan Sun <[email protected]> * Fix generated code Signed-off-by: Dan Sun <[email protected]> * Run go mod tidy Signed-off-by: Dan Sun <[email protected]> * Fix model status Signed-off-by: Dan Sun <[email protected]> --------- Signed-off-by: Dan Sun <[email protected]> * Fix LocalModelCache controller reconciles deleted resource (#4106) * Fix LocalModel controller reconciles deleted resource Signed-off-by: Sivanantham Chinnaiyan <[email protected]> * Rebase Signed-off-by: Sivanantham Chinnaiyan <[email protected]> * Fix path base routing e2e workflow Signed-off-by: Sivanantham Chinnaiyan <[email protected]> --------- Signed-off-by: Sivanantham Chinnaiyan <[email protected]> Signed-off-by: Dan Sun <[email protected]> * Add namespace to localmodel and localmodelnode ServiceAccount helm chart (#4111) add localmodelnode agent image Signed-off-by: Rituraj Singh <[email protected]> Co-authored-by: Rituraj Singh <[email protected]> Signed-off-by: Dan Sun <[email protected]> * Detect missing models and redownload models (#4095) * another squash Signed-off-by: Jin Dong <[email protected]> * Add JobTTLSecondsAfterFinished option Signed-off-by: Jin Dong <[email protected]> * Update config Signed-off-by: Jin Dong <[email protected]> * Use labels to filter jobs instead of deleting old jobs Signed-off-by: Jin Dong <[email protected]> * Add log in test Signed-off-by: Jin Dong <[email protected]> * Fix test and helm chart Signed-off-by: Jin Dong <[email protected]> * Create a seperate file system utils file Signed-off-by: Jin Dong <[email protected]> * Add comments Signed-off-by: Jin Dong <[email protected]> * Fix status update bug Signed-off-by: Jin Dong <[email protected]> --------- Signed-off-by: Jin Dong <[email protected]> Signed-off-by: Dan Sun <[email protected]> * Allow multiple node groups in the model cache CR (#4134) * Allow multiple node groups in the model cache CR Signed-off-by: Jin Dong <[email protected]> * Fix test --------- Signed-off-by: Jin Dong <[email protected]> Signed-off-by: Dan Sun <[email protected]> * Annotation to disable model cache (#4118) Signed-off-by: Jin Dong <[email protected]> Signed-off-by: Dan Sun <[email protected]> * Clean up jobs in model cache agent (#4140) * Clean up jobs Signed-off-by: Jin Dong <[email protected]> * fix lint Signed-off-by: Jin Dong <[email protected]> * Fix lint Signed-off-by: Jin Dong <[email protected]> * Fix deletion propagation policy Signed-off-by: Jin Dong <[email protected]> * Update test Signed-off-by: Jin Dong <[email protected]> --------- Signed-off-by: Jin Dong <[email protected]> Signed-off-by: Dan Sun <[email protected]> * Ensure Model root folder exists (#4142) Signed-off-by: Jin Dong <[email protected]> Signed-off-by: Dan Sun <[email protected]> * Add NodeGroup Name Into PVC Name (#4141) * Add NodeGroup Name Into PVC Name Signed-off-by: Gavin Li <[email protected]> * Add comment to fix multiple node group Signed-off-by: Dan Sun <[email protected]> * fix openvino dependency Signed-off-by: Dan Sun <[email protected]> --------- Signed-off-by: Gavin Li <[email protected]> Signed-off-by: Dan Sun <[email protected]> Co-authored-by: Dan Sun <[email protected]> Signed-off-by: Dan Sun <[email protected]> * Make LocalModel Agent reconcilation frequency configurable (#4143) * Make reconcilation configurable Signed-off-by: Jin Dong <[email protected]> * Fix codegen Signed-off-by: Jin Dong <[email protected]> * Remove a redudant space Signed-off-by: Jin Dong <[email protected]> * Rename config Signed-off-by: Jin Dong <[email protected]> * Fix lint Signed-off-by: Jin Dong <[email protected]> --------- Signed-off-by: Jin Dong <[email protected]> Co-authored-by: Dan Sun <[email protected]> Signed-off-by: Dan Sun <[email protected]> * LocalModelCache Admission Webhook (#4102) * init Signed-off-by: Gavin Li <[email protected]> * broken code Signed-off-by: Gavin Li <[email protected]> * register webhook Signed-off-by: Gavin Li <[email protected]> * rename + working Signed-off-by: Gavin Li <[email protected]> * pass in client Signed-off-by: Gavin Li <[email protected]> * check storageURI Signed-off-by: Gavin Li <[email protected]> --------- Signed-off-by: Gavin Li <[email protected]> Signed-off-by: Dan Sun <[email protected]> * Fix isvc role localmodelcache permission (#4131) * Fix localmodelcache permission for isvc Signed-off-by: Sivanantham Chinnaiyan <[email protected]> * Patch localmodelcache webhook for kubeflow overlay Signed-off-by: Sivanantham Chinnaiyan <[email protected]> --------- Signed-off-by: Sivanantham Chinnaiyan <[email protected]> Signed-off-by: Dan Sun <[email protected]> --------- Signed-off-by: Gavin Li <[email protected]> Signed-off-by: Dan Sun <[email protected]> Signed-off-by: Jin Dong <[email protected]> Signed-off-by: Sivanantham Chinnaiyan <[email protected]> Signed-off-by: Rituraj Singh <[email protected]> Co-authored-by: Gavin Li <[email protected]> Co-authored-by: Gavin Li <[email protected]> Co-authored-by: Jin Dong <[email protected]> Co-authored-by: Sivanantham <[email protected]> Co-authored-by: Rituraj Singh <[email protected]> Co-authored-by: Rituraj Singh <[email protected]>

greenmoon55 added 8 commits November 14, 2024 17:53

Delete model from LocalModelNode

10a0d1c

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

Cleanup code

b0692a8

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

Cleanup code

b7c8235

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

Fix lint

5efe1b6

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

Initializer node status map

0e8c1de

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

Update status

2269890

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

Update localmodel node status

16fba5a

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

Remove job dependency from localmodel controller

f44442c

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

greenmoon55 marked this pull request as ready for review November 15, 2024 22:28

Remove some unused lines

66d006a

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

greenmoon55 added 2 commits November 19, 2024 11:05

Merge branch 'model_cache' into update-status

535c833

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

Add comments

5578f85

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

greenmoon55 force-pushed the update-status branch from 4319c18 to 5578f85 Compare November 19, 2024 16:23

yuzisun approved these changes Nov 20, 2024

View reviewed changes

yuzisun added lgtm approved labels Nov 20, 2024

yuzisun merged commit 8f7f44e into kserve:model_cache Nov 20, 2024
46 checks passed

yuzisun mentioned this pull request Dec 1, 2024

Model cache controller and node agent #4089

Merged

9 tasks

greenmoon55 deleted the update-status branch December 23, 2024 20:46

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Update Model status from LocalModelNode status #4056

Update Model status from LocalModelNode status #4056

greenmoon55 commented Nov 15, 2024 •

edited

Loading

yuzisun commented Nov 19, 2024

yuzisun left a comment

Update Model status from LocalModelNode status #4056

Update Model status from LocalModelNode status #4056

Conversation

greenmoon55 commented Nov 15, 2024 • edited Loading

yuzisun commented Nov 19, 2024

yuzisun left a comment

Choose a reason for hiding this comment

greenmoon55 commented Nov 15, 2024 •

edited

Loading