Skip to content

Issues: kubernetes-sigs/gateway-api-inference-extension

v0.4 Release Tracker
#681 opened Apr 13, 2025 by kfswain
Open 4
Beta
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

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
Assignee
Filter by who’s assigned
Sort

Issues list

Add Inference Extension to vLLM Integrations Doc needs-triage Indicates an issue or PR lacks a `triage/foo` label and requires one.
#794 opened May 7, 2025 by danehans updated May 7, 2025
EPP HA deployment triage/accepted Indicates an issue or PR is ready to be actively worked on.
#692 opened Apr 14, 2025 by liu-cong updated May 7, 2025
2 tasks
Add the ability for scheduling plugins to add/modify requests during request processing needs-triage Indicates an issue or PR lacks a `triage/foo` label and requires one.
#791 opened May 7, 2025 by shmuelk updated May 7, 2025
What does this project think about "disaggregated prefilling"? lifecycle/rotten Denotes an issue or PR that has aged beyond stale and will be auto-closed.
#166 opened Jan 7, 2025 by spacewander updated May 7, 2025
EPP cannot serve /chat/completions API kind/bug Categorizes issue or PR as related to a bug. needs-triage Indicates an issue or PR lacks a `triage/foo` label and requires one.
#790 opened May 7, 2025 by delavet updated May 7, 2025
Support Semantic Processing using NLP models needs-triage Indicates an issue or PR lacks a `triage/foo` label and requires one.
#770 opened May 1, 2025 by rootfs updated May 6, 2025
v0.4 Release Tracker triage/accepted Indicates an issue or PR is ready to be actively worked on.
#681 opened Apr 13, 2025 by kfswain updated May 6, 2025
1 of 17 tasks
Add Performance Benchmarking to Release Doc documentation Improvements or additions to documentation triage/accepted Indicates an issue or PR is ready to be actively worked on.
#787 opened May 6, 2025 by danehans updated May 6, 2025
move updating scheduling parameters from env variables to main from scheduling pkg good first issue Denotes an issue ready for a new contributor, according to the "help wanted" guidelines. help wanted Denotes an issue that needs help from a contributor. Must meet "help wanted" guidelines. triage/accepted Indicates an issue or PR is ready to be actively worked on.
#586 opened Mar 27, 2025 by kaushikmitr updated May 6, 2025
Docs: Explain InferencePool Ownership documentation Improvements or additions to documentation help wanted Denotes an issue that needs help from a contributor. Must meet "help wanted" guidelines. triage/accepted Indicates an issue or PR is ready to be actively worked on.
#489 opened Mar 13, 2025 by danehans updated May 5, 2025
Optimize Dockerfile for Multiple Extensions good first issue Denotes an issue ready for a new contributor, according to the "help wanted" guidelines. help wanted Denotes an issue that needs help from a contributor. Must meet "help wanted" guidelines. triage/accepted Indicates an issue or PR is ready to be actively worked on.
#698 opened Apr 15, 2025 by danehans updated May 5, 2025
Tools: Add Scheduler Plugin Metrics to Dashboards triage/accepted Indicates an issue or PR is ready to be actively worked on.
#705 opened Apr 17, 2025 by danehans updated May 5, 2025
API Discrepancy: InferencePoolSpec pod selector field name mismatch between API Proposal 002 and current Go type definition documentation Improvements or additions to documentation kind/bug Categorizes issue or PR as related to a bug. triage/accepted Indicates an issue or PR is ready to be actively worked on.
#766 opened Apr 30, 2025 by SinaChavoshi updated May 5, 2025
metrics dashboard should be documented for options other than Google Managed Prometheus good first issue Denotes an issue ready for a new contributor, according to the "help wanted" guidelines. help wanted Denotes an issue that needs help from a contributor. Must meet "help wanted" guidelines. triage/accepted Indicates an issue or PR is ready to be actively worked on.
#747 opened Apr 26, 2025 by nirrozenbaum updated May 5, 2025
Enable Conformance Testing for Standalone (Non-Gateway API) EPP Implementations needs-triage Indicates an issue or PR lacks a `triage/foo` label and requires one.
#753 opened Apr 28, 2025 by SinaChavoshi updated May 5, 2025
Docs: YAML Example with multiple inference pools needs-triage Indicates an issue or PR lacks a `triage/foo` label and requires one.
#769 opened May 1, 2025 by sriumcp updated May 5, 2025
Hitless Rollout Investigation kind/bug Categorizes issue or PR as related to a bug. triage/accepted Indicates an issue or PR is ready to be actively worked on.
#557 opened Mar 21, 2025 by smarterclayton updated May 5, 2025
Proposal: EPP should support heterogeneous pods across the pool triage/needs-information Indicates an issue needs more information in order to work on it.
#715 opened Apr 20, 2025 by nirrozenbaum updated May 3, 2025
Provide alerting best practices triage/accepted Indicates an issue or PR is ready to be actively worked on.
#694 opened Apr 14, 2025 by liu-cong updated May 2, 2025
e2e CI Job help wanted Denotes an issue that needs help from a contributor. Must meet "help wanted" guidelines.
#259 opened Jan 30, 2025 by danehans updated May 2, 2025
EPP upgrade/downgrade guide triage/accepted Indicates an issue or PR is ready to be actively worked on.
#693 opened Apr 14, 2025 by liu-cong updated May 1, 2025
Docs: Create EPP Operations Guide documentation Improvements or additions to documentation help wanted Denotes an issue that needs help from a contributor. Must meet "help wanted" guidelines. triage/accepted Indicates an issue or PR is ready to be actively worked on.
#735 opened Apr 24, 2025 by danehans updated May 1, 2025
Create InferenceModel Controller triage/needs-information Indicates an issue needs more information in order to work on it.
#409 opened Feb 26, 2025 by kfswain updated Apr 29, 2025
replace InferenceModel uniquness check in code with admission validation webhook needs-triage Indicates an issue or PR lacks a `triage/foo` label and requires one.
#716 opened Apr 20, 2025 by nirrozenbaum updated Apr 29, 2025
Benchmark Test Harness triage/accepted Indicates an issue or PR is ready to be actively worked on.
#732 opened Apr 23, 2025 by kfswain updated Apr 28, 2025
ProTip! What’s not been updated in a month: updated:<2025-04-07.