Skip to content

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

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.

Sign up for GitHub

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

88 Open 164 Closed
88 Open 164 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
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Adaptive metrics probing periods
#667 opened Apr 8, 2025 by ahg-g
It should be possible to use InferencePool without ext_proc
#660 opened Apr 8, 2025 by howardjohn
5
Add Envoy AI Gateway Guides
#651 opened Apr 5, 2025 by Xunzhuo
Make Version specific sets of the getting started guide
#610 opened Mar 28, 2025 by kfswain
A metric in LoRA syncer tracking loaded adapters
#600 opened Mar 28, 2025 by ahg-g
Add a metric to track InferenceModels ready to serve by the epp 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.
#598 opened Mar 28, 2025 by ahg-g
lora-syncer should block on startup until the server is ready kind/bug Categorizes issue or PR as related to a bug.
#597 opened Mar 28, 2025 by ahg-g
1
CPU deployment naming needs cleanup
#594 opened Mar 27, 2025 by kfswain
@nirrozenbaum
1
support grayscale processes based on basic models
#587 opened Mar 27, 2025 by zgqqiang
4
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.
#586 opened Mar 27, 2025 by kaushikmitr
lora-syncer tool's error handling needs improvement kind/bug Categorizes issue or PR as related to a bug.
#584 opened Mar 26, 2025 by kfswain
EPP TLS support provides very minimal protection kind/feature Categorizes issue or PR as related to a new feature.
#582 opened Mar 26, 2025 by LiorLieberman
3
Metric showing latency to make a placement decision kind/bug Categorizes issue or PR as related to a bug.
#581 opened Mar 26, 2025 by smarterclayton
Include metadata metric
#579 opened Mar 26, 2025 by JeffLuoo
1
Record the limitation that only a single EPP replica has been tested so far
#572 opened Mar 25, 2025 by ahg-g
Improve vLLM upstream health checks to only pass when models are servable
#558 opened Mar 21, 2025 by smarterclayton
During hitless rollout testing, on average one early request to vLLM times out. kind/bug Categorizes issue or PR as related to a bug.
#557 opened Mar 21, 2025 by smarterclayton
1
Configure x-request-id support in the default ootb examples kind/bug Categorizes issue or PR as related to a bug.
#556 opened Mar 21, 2025 by smarterclayton
Improve metric capture on error
#554 opened Mar 20, 2025 by kfswain
1
We should encourage all InferencePool deployments to gracefully rollout and drain kind/bug Categorizes issue or PR as related to a bug.
#549 opened Mar 20, 2025 by smarterclayton
@smarterclayton
2
Remove k8s dependency from BBR
#535 opened Mar 19, 2025 by rramkumar1
Add a helm chart to parameterize the benchmark guide so users don't need to fork the repo
#528 opened Mar 18, 2025 by liu-cong
Unable to know when gateway extension is scraped, no log line printed kind/bug Categorizes issue or PR as related to a bug.
#525 opened Mar 18, 2025 by smarterclayton
Add a more detailed user manual (initial version)
#523 opened Mar 17, 2025 by liu-cong
3 tasks
1
Consider backend augmentation vs new backend type
#521 opened Mar 17, 2025 by howardjohn
1
ProTip! Updated in the last three days: updated:>2025-04-05.