Skip to content

Issues: vllm-project/production-stack

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

28 Open 47 Closed
28 Open 47 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

feature: Detect PII in HTTP request feature request New feature or request
#227 opened Mar 5, 2025 by rootfs
1
feature: Support LoRA loading for model deployments feature request New feature or request
#205 opened Mar 1, 2025 by ApostaC
feature: Support CRD based configuration feature request New feature or request
#204 opened Mar 1, 2025 by rootfs
bug: "POST /v1/chat/completions HTTP/1.1" 503 Service Unavailable bug Something isn't working
#201 opened Feb 28, 2025 by corona10
2
[WIP, RFC] Production Stack on Ray Serve discussion
#195 opened Feb 27, 2025 by Hanchenli
4
bug: File Access Error with vllm using runai_streamer on OCP bug Something isn't working
#193 opened Feb 27, 2025 by TamKez
5
feature: custom callback functionality in vllm-router feature request New feature or request help wanted Extra attention is needed
#186 opened Feb 26, 2025 by pwuersch
1
feature: introduce pyproject.toml and use uv feature request New feature or request good first issue Good for newcomers help wanted Extra attention is needed
#184 opened Feb 25, 2025 by bufferoverflow
1
feature: unify naming of production-stack, vllm-stack and vllm-router discussion feature request New feature or request
#178 opened Feb 25, 2025 by bufferoverflow
5
feature: Terraform Quickstart Tutorials for Google GKE feature request New feature or request
#172 opened Feb 23, 2025 by falconlee236
5
feature: Terraform Quickstart Tutorials for Underlying Infrastructure feature request New feature or request
#167 opened Feb 21, 2025 by 0xThresh
2
Discussion - QPS routing when there are multiple router replicas discussion question Further information is requested
#166 opened Feb 21, 2025 by aishwaryaraimule21
2
bug: flaky test case Functionality test for helm chart / Multiple-Models bug Something isn't working
#152 opened Feb 19, 2025 by gaocegege
2
bug: Model not found when enable vllm api key bug Something isn't working
#150 opened Feb 18, 2025 by JustinDuy
1
8
[WIP] Amazon EKS tutorial + Azure + GKE tutorial,
#129 opened Feb 14, 2025 by Hanchenli
@truskovskiyk @Hanchenli @EaminC
5
Discussion: Pipeline parallelism support
#101 opened Feb 10, 2025 by Shaoting-Feng
6
Discussion: Unifying versions for helm and router question Further information is requested
#80 opened Feb 7, 2025 by gaocegege
11
Feat: Router observability (Current QPS, router-side queueing delay, etc) feature request New feature or request
#78 opened Feb 7, 2025 by sitloboi2012
@sitloboi2012
3
feat: Distributed tracing for router feature request New feature or request help wanted Extra attention is needed
#77 opened Feb 7, 2025 by gaocegege
@Sozhan308
3
feat: Allow remote backend configuration feature request New feature or request
#75 opened Feb 7, 2025 by askulkarni2
@ApostaC
1
Why Hugging Face Token? question Further information is requested
#67 opened Feb 6, 2025 by nitin302
2
Create an Example Building Ingress for Router Service documentation Improvements or additions to documentation
#60 opened Feb 4, 2025 by 0xThresh
1
@0xThresh
[RFC] prefix-cache-aware routing
#59 opened Feb 4, 2025 by KuntaiDu
34
Helm Chart Lacks Clear Support for Multi-Node vLLM Deployment help wanted Extra attention is needed
#50 opened Jan 31, 2025 by shohamyamin
11
feat: Offline batched inference based on OpenAI offline batching API feature request New feature or request
#47 opened Jan 31, 2025 by gaocegege
3
ProTip! no:milestone will show everything without a milestone.