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.

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

ci updates #18

Merged
merged 13 commits into from
Jan 10, 2018
Merged

ci updates #18

merged 13 commits into from
Jan 10, 2018

Conversation

gsunner
Copy link
Contributor

@gsunner gsunner commented Jan 10, 2018

No description provided.

@gsunner gsunner merged commit 6b93941 into SeldonIO:master Jan 10, 2018
agrski pushed a commit that referenced this pull request Dec 2, 2022
* Initial commit for REST reverse proxy

* refactor and use v2client

* initial cache manager

* add LRU functionality

* fix LRU test

* wire up cache

* Add locking and tests

* add  edge case tests

* tidy up test

* tidy up tests and add concurrent update

* add a test for extract model name from path

* initial state manager strucutre

* rename file

* adding locking

* unload model when we evict

* go mod changes

* fix test

* retun priority when evict as well

* integrate cache in reverse proxy

* wire up state manager in client

* tidy up get model details

* wire up reverse proxy at start

* Change model version to unit32

* Initial Agent version changes. Code refactor.

* lint and ensure model name is changed

* Add unload model functionality to agent to handle versions

* Add version cleanup to scheduler

* Updates for k8s

* lint

* small updates

* change download to use hash for rclone folder to eventually allow caching of copy sync

* Modify protos to remove version and restructure

* k8s testing via grpc

* Update operator

* ensure k8s generation works

* Allow multiple vesions in ModelStatus call

* Handle terminate and k8s updates

* lint

* add retry for status update and fix event creation

* lint

* fix retries for client -> scheduler

* Add triton server handler to agent

* grpc test

* Add Triton

* fix server http port typos

* Fix Envoy resource bug and add server memory notebook tests

* Add triton xgboost example and always copy triton config

* lint

* Initial Manager reconcile for Server

* Add servers to kustomize

* Updates for agent start from env and updates to serverconfigs

* Add Status Handling for Servers

* handle deleted servers and consistent ordering of replicas

* Add logging

* sync model reload with concurrent infer requests

* Add Server Notification and events

* buggy wg

* review comments changes

* lint

* change minReplicas to 1 if not specified

* remove unnecesary get model

* fix test

* wait on concurrent model reload

* fix model reschedule to server on server delete

* better reverse proxy lifecycle management

* updated to fix delete server tests in k8s notebook

* lint

* review comments for client state

* implement delete item using the heap Remove util

* fix test after merge

* Move channel comms to central hub

* improve agent server tests

* lint

* review comment updates

* Fix hub channel close safety

* review comment updates

* Make addListener signal type of channel

* Set channel as send only for config updates

* update Makefile to allow servers to be deployed

* Update scheduler server deployment (as opposed to operator server deployment) and add debug for filters when they fail in scheduling

* lint

* Updates from review

* fix typos

* Agent Service for debugging

* makefile changes

* return more state in status endpoint

* changes to notebook

* further changes post-merge

* tidy up logic for concurrency management

* tidy up interface for clientservices

* tidy up test

* serialise actions on same model (control plane)

* Add a test for concurrent unload

* tidy up code

* if there is an error in makeroom try next model

* add test data and control plane

* tidy up some of the concurrency

* deal with concurrency  parallel unload

* having locks per model across entire stack

* sorting out concurrency issues

* fix deadlock

* tidy up test

* check memory server capacity before update

* return 404 if the model cannot be found / reloaded

* fix reverse proxy test

* notebook changes

* notebook changes

* post merge #2

* fix lint

* notebook changes

* export reverse proxy ports

* refactor function

Co-authored-by: Clive Cox <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

1 participant