Sync main branch changes to release-0.1 branch #375
Merged
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 sync images step and scripts in release process
* e2e driver and test * comment functions * check job status in test * format update * update copyright * add examples with instructions and interfaces * move batch tutorial --------- Co-authored-by: xin.chen <xin.chen@bytedance.com>
add uvicorn startup into file entrypoint
* Use model name from request body * rename dummy to reserved router
* skip docs CI if no changes in /docs dir * test docs build
* improve rayclusterreplicaset status * nit * fix lint error * improve isClusterActive logic * fix lint error * remove redundant isRayPodCreateOrDeleteFailed check --------- Signed-off-by: Yicheng-Lu-llll <luyc58576@gmail.com>
* Add request trace for profiling * add to redis at 10 second interval * nit * round to nearest 10s interval * round timestamp to nearest 10s interval and aggregate data by model * add go routine to add request trace
#295 introduce the latest kuberay api and the dependencies bumps sigs.k8s.io/controller-runtime from v0.17.3 to v0.17.5. Due to that change, make manifest update the CRD definitions
* Disable docker build github workflow to cut CI cost * Push images to Github registry in release pipeline
* minor clean up on the autoscaler controller * Extract the algorithm package algorithm is extracted to distinguish with the scaler. * Refactor scaler interface 1. Split the Scaler interface and BaseAutoscaler implementation 2. Create APA/KPA scaler separately and adopt the corresponding algorithms * Introduce the scalingContext in algorithm * Introduce k8s.io/metrics for resource & custom metrics fetching * Extract metric fetcher to cover the fetching logic * Optimize the scaler workflow to adopt fetch and client interface * Further refactor the code structure
* Support pod autoscaler periodically check * Fix the error case
* Refactor AutoScaler: optimize metric client, context, and reconcile processes. * fix make lint-all * fix typos
* doc: update runtime readme * update doc title
* Add env for routing strategy override * nit * update code to merge quality
* Fix pod autoscaler enqueue issues * Fix the wrong package name
* Add autoscaling benchmark scripts * Update application to support kv cache utilization and metrics override * fix kpa reconcilation issue * add debug mode into fetcher, fix kpa log output * add benchmark generator * Enable LoadBalancer and update model name * Update autoscaling files * Update metric name * Update the yamls * fix --------- Co-authored-by: Jiaxin Shan <seedjeffwan@gmail.com>
Add lora benchmark guidance and scripts Update scripts
add plotting script Co-authored-by: Le Xu <le.xu@bytedance.com>
* Add ipv6 support for envoyproxy * Enable ipv6 for envoy proxy * revert namespace change
* Add gateway benchmark scripts * Update the consistent traffic client * Add model file
* use TOS as batch request storage * update format check * file with test * update tos with volcano TOS and add an initialization for storage * update format * address comments * remove main * update log format * update log format --------- Co-authored-by: xin.chen <xin.chen@bytedance.com>
* Add check if no pods are present * nit update * Add unit test
* fix: disable fastapi docs in runtime default action * format
* refact: runtime server startup with args * docs: update runtime startup command * fix log print * fix runtime entrypoint in Dockerfile * fix dockerfile
* add ruff lint and format rules * add format scripts * doc: format * add version check * refact: tool version check * format with new rules
* optimize workload scripts and result output * add more logs. resync period: 30->10, fix kpa.yaml * fix lint * add right klog level. unify min-replica in hpa.yaml and hpa.yaml * unify hpa and kpa yaml min-replica to 1
1. Remove useless files, users should always follow the top level README.md to install the control plan, this is the mocked app folder and people should leverage mocked app from there rather than any other aibrix components. This is good for consistency as well. 2. Change app namespace from aibrix-system to default. The old deployment in aibrix-system hides a lots of edge cases and issues, in real world envs, we won’t deploy data plane workloads in control plane namespace. Change to default to mock the real case. 3. Update README.md structure and make it cleaner to adopt above changes
* Make sure service name is aligned with model.aibrix.ai/name value This is to avoid httproute backend ref name mismatch issue * Update docs about service httproute naming trick
* Validate routing strategy bug fix * add unit tests * add header in gateway_test.go
* Bug fix for setting routing strategy via env var * remove default routing algorithm env var
* Add more debug information from input side * Add the utils to get routing value & enabled part * Update the unit tests * Fix the lint issue
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.
Pull Request Description
git reset --hard HEAD^to v0.1.0-rc3. This is because we use squash merge for v0.1.0-rc4 last time.mergethis time to keep the commitRelated Issues
Resolves: #[Insert issue number(s)]
Important: Before submitting, please complete the description above and review the checklist below.
Contribution Guidelines (Expand for Details)
We appreciate your contribution to aibrix! To ensure a smooth review process and maintain high code quality, please adhere to the following guidelines:
Pull Request Title Format
Your PR title should start with one of these prefixes to indicate the nature of the change:
[Bug]: Corrections to existing functionality[CI]: Changes to build process or CI pipeline[Docs]: Updates or additions to documentation[API]: Modifications to aibrix's API or interface[CLI]: Changes or additions to the Command Line Interface[Misc]: For changes not covered above (use sparingly)Note: For changes spanning multiple categories, use multiple prefixes in order of importance.
Submission Checklist
By submitting this PR, you confirm that you've read these guidelines and your changes align with the project's contribution standards.