Sync #159
Merged
Sync #159
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
* Add CA bundle configuration Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * Implement CA bundle volume mount Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * Update tests Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * Add default mount path Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * Update defaults Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * Update constants Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * Use constant Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * Implement tests Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * Rename volume Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * Fix name references Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * Update configmap Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> * fix unit test for pr-3216 Signed-off-by: jooho <jlee@redhat.com> * add a logic to mount cabundle secret to storage-initializer container Signed-off-by: jooho <jlee@redhat.com> * Correct failed conflict resolve of storage_initializer_injector.go Signed-off-by: Christian Kadner <ckadner@us.ibm.com> * Revert changes in go.sum Signed-off-by: Christian Kadner <ckadner@us.ibm.com> * Revert changes in zz_generated.deepcopy.go Signed-off-by: Christian Kadner <ckadner@us.ibm.com> * Revert changes in openapi_generated.go Signed-off-by: Christian Kadner <ckadner@us.ibm.com> * Revert changes in zz_generated.deepcopy.go Signed-off-by: Christian Kadner <ckadner@us.ibm.com> * convert Secret to ConfigMap for cabundle Signed-off-by: jooho <jlee@redhat.com> * update some sources to solve reviews Signed-off-by: jooho <jlee@redhat.com> * Add 'cabundle_configmap' to 'storage-config' StorageSpec Signed-off-by: jooho <jlee@redhat.com> * fix new comments Signed-off-by: jooho <jlee@redhat.com> * update to fix review comments Signed-off-by: jooho <jlee@redhat.com> --------- Signed-off-by: Danilo Peixoto <danilopeixoto@outlook.com> Signed-off-by: Dan Sun <dsun20@bloomberg.net> Signed-off-by: jooho <jlee@redhat.com> Signed-off-by: Christian Kadner <ckadner@us.ibm.com> Signed-off-by: Jooho Lee <jlee@redhat.com> Co-authored-by: Danilo Peixoto <danilopeixoto@outlook.com> Co-authored-by: Dan Sun <dsun20@bloomberg.net> Co-authored-by: Christian Kadner <ckadner@us.ibm.com>
Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>
* Update Istio-Dex docs Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Add docs for auth using service account Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Fix kfserving name Signed-off-by: Dan Sun <dsun20@bloomberg.net> --------- Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> Signed-off-by: Dan Sun <dsun20@bloomberg.net> Co-authored-by: Dan Sun <dsun20@bloomberg.net>
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
…loadModel() (kserve#3295) Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
…rror in future (kserve#3272) * Update ray serve version Update tests to remove detached=false parameter Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> * Pinned `async-timeout` as direct dependency for python 3.11 Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> --------- Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com>
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
* Fix qpext hangs during shutdown Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Fix e2e qpext image build Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Revert vcs info stamping Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> --------- Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>
chore: Upgrade to XGBoost v2.0.2 Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
* fix: Check if HPA has the same scaleTargetRef Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * Update pkg/controller/v1beta1/inferenceservice/reconcilers/hpa/hpa_reconciler.go Co-authored-by: Jooho Lee <ljhiyh@gmail.com> Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * chore: simplify semanticHPAEquals Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * chore: simplify Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> --------- Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> Co-authored-by: Jooho Lee <ljhiyh@gmail.com>
kserve#3311) * Updated quick_install script. Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> * Use existing variables for checking versions Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> * Fixed typo mistakes. Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> --------- Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com>
* replace github.com/golang/protobuf Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * regenerate tf2openapi Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * remove use of github.com/gogo/protobuf pkg Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> --------- Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>
* Add health check probe for controller manager Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * fmt Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * make manifests Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Remove startup probe Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Update helm chart Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> --------- Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>
* Move ksvc dry run logic inside retry Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * remove retry on ig and isvc Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> --------- Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>
Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> Signed-off-by: andy <andrews.arokiam@ideas2it.com>
… than the total model features on lightgbm (kserve#3313) Fix inference request fails when sending with less number of features than the total model features Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>
* Add a CI_USE_ISVC_HOST for testing with the ISVC hostname This adds the possibility to run E2E tests using the hostname specified in the `status.url` field of the InferenceServices, rather than using the ClusterIP of the Istio Ingress gateway. This behavior is enabled by, first, setting the `CI_USE_ISVC_HOST=1` environment variable and, then invoking pytest. Thus, the original behavior of using Istio IngressGateway ClusterIP is the default one. Signed-off-by: Edgar Hernández <23639005+israel-hdez@users.noreply.github.com> * Add a CI_USE_ISVC_HOST for testing with the ISVC hostname This adds the possibility to run E2E tests using the hostname specified in the `status.url` field of the InferenceServices, rather than using the ClusterIP of the Istio Ingress gateway. This behavior is enabled by, first, setting the `CI_USE_ISVC_HOST=1` environment variable and, then invoking pytest. Thus, the original behavior of using Istio IngressGateway ClusterIP is the default one. Signed-off-by: Edgar Hernández <23639005+israel-hdez@users.noreply.github.com> --------- Signed-off-by: Edgar Hernández <23639005+israel-hdez@users.noreply.github.com>
* Upgraded poetry version to 1.7.1 Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> * fixed poetry install with invalid group. python-poetry/poetry#7529 Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com> --------- Signed-off-by: Andrews Arokiam <andrews.arokiam@ideas2it.com>
Signed-off-by: David van der Spek <vanderspek.david@gmail.com>
… of transformer container port in transformer collocation (kserve#3318) * Fix service points to predictor in raw deployment collocation Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Set readiness probe for transformer container Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Add e2e test Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * resolve comments Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> --------- Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com>
Upgrade cloudevents to v2 Signed-off-by: Dan Sun <dsun20@bloomberg.net> Co-authored-by: Dan Sun <dsun20@bloomberg.net>
…and predictor (kserve#3280) * Restrict storage uri to predictor only in transformer collocation Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Add unit tests Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Add e2e test Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * fmt Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Fix e2e test debug info Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Improve quick install script Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Update docs Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * fix indentation on quick install Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> --------- Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> Signed-off-by: Dan Sun <dsun20@bloomberg.net> Co-authored-by: Dan Sun <dsun20@bloomberg.net>
* Add new storageUri schema "oci" that points to a OCI image For that a new injector that adds a so-called "modelcar" container to "kserve-container" as a sidecar has been added. This setups a pod for sharing the process namespace (shareProcessNamespace = true). The following configuration options have been added: * `enableModelcar` to switch on this feature (default: false) * `cpuModelcar` and `memoryModelcar` to set the resources for the modelcar container * `uidModelcar` for the UID to use for the user-container *and* the modelcar contained See kserve#3110 for more information and architecture of this feature. Signed-off-by: Roland Huß <rhuss@redhat.com> * Fix merge Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Allow oci prefix Signed-off-by: Dan Sun <dsun20@bloomberg.net> --------- Signed-off-by: Roland Huß <rhuss@redhat.com> Signed-off-by: Dan Sun <dsun20@bloomberg.net> Co-authored-by: Dan Sun <dsun20@bloomberg.net>
* Add regex support for propagating IG headers Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Address comments Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Log headers that are propagated Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * Add test case for invalid pattern Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> * resolve comments Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> --------- Signed-off-by: Sivanantham Chinnaiyan <sivanantham.chinnaiyan@ideas2it.com> Signed-off-by: Dan Sun <dsun20@bloomberg.net> Co-authored-by: Dan Sun <dsun20@bloomberg.net>
* chore: Prepare v0.12.0-rc0 release Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> Signed-off-by: Dan Sun <dsun20@bloomberg.net> * python version should not contain dash Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> Signed-off-by: Dan Sun <dsun20@bloomberg.net> * modelmeshVersion bump and python packages bump Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Update helm values Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Update release Signed-off-by: Dan Sun <dsun20@bloomberg.net> --------- Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> Signed-off-by: Dan Sun <dsun20@bloomberg.net> Co-authored-by: Dan Sun <dsun20@bloomberg.net>
* docs: Minor corrections/edits on release process Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * Update RELEASE_PROCESS_v2.md Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * Update RELEASE_PROCESS_v2.md Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * Update RELEASE_PROCESS_v2.md Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> --------- Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
…ixes kserve#3314 (kserve#3315) * build: Switch to use kustomize in kubectl to simplify build process. Fixes kserve#3314 Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * Update scripts in hack folder Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * Address comments Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * Revert incorrect change Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> --------- Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
…3301) * feat: Expose defaults for several batcher handler parameters Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * fix: add timeout Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * Add new params to config/manifests Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * Remove timeout Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> --------- Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
…ixes kserve#3323 (kserve#3321) * fix: Properly close resources and handle errors in agent and storage Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * reduce indentation Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * return early Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * return -> break Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * Address comments Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * newError -> closeErr Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> * newError -> closeErr Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> --------- Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
…3332) * Update bert tokenizer example Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Generate id for infer request Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix model name in tests Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix model_name argument Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix predictor_protocol Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Generate request id if none Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Set default None for PredictorConfig Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Add comment Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Enable doc with default values Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Add back add_help false Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Update protocol choices Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Fix grpc-v2 choice Signed-off-by: Dan Sun <dsun20@bloomberg.net> --------- Signed-off-by: Dan Sun <dsun20@bloomberg.net>
Signed-off-by: Yuan Tang <terrytangyuan@gmail.com>
* Update kserve python runtime API docstring Signed-off-by: Dan Sun <dsun20@bloomberg.net> * Use InferenceError Signed-off-by: Dan Sun <dsun20@bloomberg.net> --------- Signed-off-by: Dan Sun <dsun20@bloomberg.net>
|
[APPROVALNOTIFIER] This PR is APPROVED This pull-request has been approved by: spolti The full list of commands accepted by this bot can be found here. The pull request process is described here
Needs approval from an approver in each of these files:
Approvers can indicate their approval by writing |
Signed-off-by: Spolti <fspolti@redhat.com>
|
/lgtm |
openshift-merge-bot
bot
merged commit 2d53808
into
opendatahub-io:master
26 checks passed
israel-hdez
pushed a commit
to israel-hdez/kserve
that referenced
this pull request
Mar 1, 2024
…p/component-updates/kserve-agent-28 Update kserve-agent-28 to 24e1fc7
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
What this PR does / why we need it:
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.
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
Logs
Special notes for your reviewer:
Checklist:
Release note: