Skip to content

Issues: vllm-project/aibrix

v0.3.0 roadmap
#698 opened Feb 18, 2025 by Jeffwan
Open 9
Research & Industry Collaboration Invitation
#699 opened Feb 18, 2025 by Jeffwan
Open 3
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

147 Open 301 Closed
147 Open 301 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

prefix cache aware routing is not truly prefix cache area/gateway area/performance priority/critical-urgent Highest priority. Must be actively worked on as someone's top priority right now.
#917 opened Mar 28, 2025 by firebook
4
Failed to run RayFleet when using hostNetwork area/distributed priority/important-soon Must be staffed and worked on either currently, or very soon, ideally in time for the next release.
#915 opened Mar 28, 2025 by vaaandark
@Jeffwan
3
kv cache deploy the model across different GPUs, it create two etcd pod!
#910 opened Mar 27, 2025 by ying2025
How to deal with schedule-cache gap when scheduler is updating?
#906 opened Mar 26, 2025 by justadogistaken
How to change the envoy abrix-system-arbix-eg-903790dc image according to the actual situation of my environment?
#904 opened Mar 26, 2025 by ying2025
1
Move the benchmark codes to aibrix python package area/benchmark area/performance kind/feature Categorizes issue or PR as related to a new feature.
#903 opened Mar 25, 2025 by Jeffwan
@happyandslow
What is the minimum k8s version requirement?
#902 opened Mar 25, 2025 by zhaotyer
2
Pod Init RDMA failed!Invalid RDMA endpoint: Fall back to TCP area/kv-cache kind/documentation Improvements or additions to documentation
#897 opened Mar 24, 2025 by ying2025
5
[RFC]: New eviction strategy for prefix cache indexer area/gateway kind/feature Categorizes issue or PR as related to a new feature.
#892 opened Mar 21, 2025 by vie-serendipity
@vie-serendipity
3
[KVCache (Vineyard)] Do we need PodAffinity for model name in kvcache crd needs proper reconciliation? area/distributed area/kv-cache
#876 opened Mar 17, 2025 by gangmuk
@Jeffwan @DwyaneShi
2
[Vineyard] vllm engine crashes, failing to connect to vineyard when starting the pod. area/distributed area/kv-cache
#874 opened Mar 17, 2025 by gangmuk
@Jeffwan @DwyaneShi
5
Separate CRDs from manifest installation area/autoscaling area/installation priority/important-soon Must be staffed and worked on either currently, or very soon, ideally in time for the next release.
#873 opened Mar 17, 2025 by Jeffwan
1
[Dist KV] vllm pods which do not have kvcache pods running in the same node crashes. area/installation area/kv-cache kind/bug Something isn't working kind/enhancement New feature or request priority/critical-urgent Highest priority. Must be actively worked on as someone's top priority right now.
#863 opened Mar 14, 2025 by gangmuk
@DwyaneShi
1
Pluggable Gateway
#861 opened Mar 14, 2025 by danehans
4
Documentation is not clearly defined on how to set the RateLimiting and how to measure the token consumption and how to enable the authentication for different users area/gateway kind/support Categorizes issue as a support question.
#859 opened Mar 13, 2025 by vivekrsintc
@varungup90
5
Error: Invalid character 'u' looking for beginning of value area/gateway kind/support Categorizes issue as a support question. triage/needs-information Indicates an issue needs more information in order to work on it.
#858 opened Mar 13, 2025 by vivekrsintc
6
Automate local disk management and ai runtime model management area/runtime kind/feature Categorizes issue or PR as related to a new feature. priority/important-soon Must be staffed and worked on either currently, or very soon, ideally in time for the next release.
#854 opened Mar 12, 2025 by Jeffwan
Pod scale success,aibrix-controller-manager failed to parse metrics area/autoscaling kind/support Categorizes issue as a support question. triage/needs-information Indicates an issue needs more information in order to work on it.
#852 opened Mar 12, 2025 by ying2025
3
[RFC]: Make API Gateway interface OpenAI compatible area/gateway kind/enhancement New feature or request priority/critical-urgent Highest priority. Must be actively worked on as someone's top priority right now.
#846 opened Mar 11, 2025 by Jeffwan
[Observation] Improve AIBrix control plane monitoring area/stability kind/feature Categorizes issue or PR as related to a new feature. priority/important-longterm Important over the long term, but may not be staffed and/or may need multiple releases to complete.
#845 opened Mar 11, 2025 by Jeffwan
[Docs] Provide AIBrix upgrade guidance area/installation kind/documentation Improvements or additions to documentation priority/important-soon Must be staffed and worked on either currently, or very soon, ideally in time for the next release.
#844 opened Mar 11, 2025 by Jeffwan
[RFC] Support inference engine SGLang area/distributed area/performance kind/enhancement New feature or request
#843 opened Mar 11, 2025 by Belyenochi
1
Ask for testing suggestions kind/support Categorizes issue as a support question. triage/needs-information Indicates an issue needs more information in order to work on it.
#842 opened Mar 10, 2025 by ying2025
@varungup90 @gangmuk
20
OSError: /models/deepseek-r1 does not appear to have a file named configuration_deepseek.py. Checkout 'https://huggingface.co//models/deepseek-r1/tree/None' for available files.
#834 opened Mar 9, 2025 by Jeffwan
@Jeffwan
8
Some prompts with special character fail the benchmark script area/benchmark kind/bug Something isn't working priority/important-soon Must be staffed and worked on either currently, or very soon, ideally in time for the next release.
#832 opened Mar 9, 2025 by Jeffwan
ProTip! Mix and match filters to narrow down what you’re looking for.