Skip to content

Pull requests: kubernetes-sigs/gateway-api-inference-extension

New pull request New
62 Open 1,718 Closed
62 Open 1,718 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

logging: standardize EPP log levels with DEFAULT constants cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/cleanup Categorizes issue or PR as related to cleaning up code, process, or technical debt. kind/documentation Categorizes issue or PR as related to documentation. size/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#2715 opened Mar 28, 2026 by LukeAVanDrie Loading…
5
Add trtllm-serve as a built-in engine type for metric scraping cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#2713 opened Mar 27, 2026 by BenjaminBraunDev Loading…
1
3
docs: update release process for sub-modules cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/documentation Categorizes issue or PR as related to documentation. size/XS Denotes a PR that changes 0-9 lines, ignoring generated files.
#2711 opened Mar 27, 2026 by LukeAVanDrie Loading…
2
[grpc] add support for vLLM gRPC Embed endpoint in vllmgrpc-parser cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2710 opened Mar 27, 2026 by zetxqx Loading…
2
cleanup: modernize codebase using Go 1.26 go fix suite cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/cleanup Categorizes issue or PR as related to cleaning up code, process, or technical debt. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2708 opened Mar 27, 2026 by LukeAVanDrie Loading…
4
cleanup: remove stale dead code (>1 mo old) cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/cleanup Categorizes issue or PR as related to cleaning up code, process, or technical debt. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2707 opened Mar 27, 2026 by LukeAVanDrie Loading…
10
refactor: Replace NamespacedName with EndPointKey for endpoint identification cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. do-not-merge/hold Indicates that a PR should not merge because someone has issued a /hold command. kind/cleanup Categorizes issue or PR as related to cleaning up code, process, or technical debt. size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#2705 opened Mar 27, 2026 by zetxqx Loading…
4
fix: lora-syncer gracefully handles adapter load failures without blocking cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/bug Categorizes issue or PR as related to a bug. needs-ok-to-test Indicates a PR that requires an org member to verify it is safe to test. size/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#2702 opened Mar 27, 2026 by gyliu513 Loading…
1
6
fix: explain InferencePool ownership cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. needs-ok-to-test Indicates a PR that requires an org member to verify it is safe to test. size/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#2701 opened Mar 27, 2026 by gyliu513 Loading…
1
3
Add latency admission sub-plugin for SLO-based request shedding approved Indicates a PR has been approved by an approver from all required OWNERS files. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2695 opened Mar 26, 2026 by kaushikmitr Loading…
7
Add latency scorer sub-plugin for headroom-based endpoint scoring approved Indicates a PR has been approved by an approver from all required OWNERS files. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#2694 opened Mar 26, 2026 by kaushikmitr Loading…
10
Feature/add slo metrics to flowcontrol cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/feature Categorizes issue or PR as related to a new feature. needs-ok-to-test Indicates a PR that requires an org member to verify it is safe to test. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2685 opened Mar 24, 2026 by loicmarchal Loading…
1
6
feat(epp): Add plugin lifecycle and stability levels proposal cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/documentation Categorizes issue or PR as related to documentation. kind/feature Categorizes issue or PR as related to a new feature. needs-ok-to-test Indicates a PR that requires an org member to verify it is safe to test. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2684 opened Mar 24, 2026 by hexfusion Loading…
1
11
fix: add read lock to AllOrderedPriorityLevels to prevent data race cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/bug Categorizes issue or PR as related to a bug. needs-ok-to-test Indicates a PR that requires an org member to verify it is safe to test. size/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#2674 opened Mar 23, 2026 by gyliu513 Loading…
3
[WIP] Generalize the request type passed down the framework plugins: move parser out of director cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. kind/feature Categorizes issue or PR as related to a new feature. needs-ok-to-test Indicates a PR that requires an org member to verify it is safe to test. size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#2673 opened Mar 23, 2026 by RyanRosario Loading…
1
36
Decompose predictedlatency plugin into 3 composable sub-plugins cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. size/XXL Denotes a PR that changes 1000+ lines, ignoring generated files.
#2667 opened Mar 23, 2026 by kaushikmitr • Draft
7
Optimize routing for multimodal inputs with image/video URLs in the request cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2666 opened Mar 23, 2026 by rahulgurnani • Draft
5
test: refactor integration test harness to support data layer testing cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. needs-rebase Indicates a PR cannot be merged because it has merge conflicts with HEAD. ok-to-test Indicates a non-member PR verified by an org member that is safe to test. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2664 opened Mar 23, 2026 by Mohamedma96 Loading…
1
42
fix(test): Add unit test for prediction approved Indicates a PR has been approved by an approver from all required OWNERS files. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. ok-to-test Indicates a non-member PR verified by an org member that is safe to test. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2662 opened Mar 22, 2026 by gyliu513 Loading…
6
[Fix] Datalayer error handling cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. kind/bug Categorizes issue or PR as related to a bug. kind/documentation Categorizes issue or PR as related to documentation. size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#2660 opened Mar 22, 2026 by elevran Loading…
2
WIP: Minimal refactoring to have a single shard approved Indicates a PR has been approved by an approver from all required OWNERS files. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. kind/cleanup Categorizes issue or PR as related to cleaning up code, process, or technical debt. lgtm "Looks good to me", indicates that a PR is ready to be merged. size/XL Denotes a PR that changes 500-999 lines, ignoring generated files.
#2658 opened Mar 22, 2026 by shmuelk Loading…
@LukeAVanDrie
17
feat: Add unit test for single_profile_handler.go cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. ok-to-test Indicates a non-member PR verified by an org member that is safe to test. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2656 opened Mar 22, 2026 by gyliu513 Loading…
5
[feat] Latency Prediction CI tests area/conformance-test Issues or PRs related to Conformance tests. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. do-not-merge/work-in-progress Indicates that a PR should not merge because it is a work in progress. kind/feature Categorizes issue or PR as related to a new feature. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2651 opened Mar 20, 2026 by Gregory-Pereira • Draft
3
token_estimator: handles Responses and Conversations API cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. ok-to-test Indicates a non-member PR verified by an org member that is safe to test. size/M Denotes a PR that changes 30-99 lines, ignoring generated files.
#2647 opened Mar 20, 2026 by RishabhSaini Loading…
8
Unit test fixes - Add missing test cases for new datalayer metrics. cncf-cla: yes Indicates the PR's author has signed the CNCF CLA. lgtm "Looks good to me", indicates that a PR is ready to be merged. ok-to-test Indicates a non-member PR verified by an org member that is safe to test. size/L Denotes a PR that changes 100-499 lines, ignoring generated files.
#2640 opened Mar 20, 2026 by Mohamedma96 Loading…
1
@elevran
22
ProTip! Filter pull requests by the default branch with base:main.