Skip to content

Issues: kubernetes-sigs/inference-perf

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.

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

24 Open 14 Closed
24 Open 14 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

Update all url fields types from str to pydantics HttpUrl
#78 opened May 19, 2025 by Bslabe123
Add Ability to Query Metrics from Google Managed Prometheus
#76 opened May 13, 2025 by Bslabe123
Report Generation for multi-stage runs
#70 opened May 8, 2025 by aish1331
@aish1331
2
make validate does not catch circular imports
#69 opened May 7, 2025 by Bslabe123
Make lint checks blocking for PR merges
#63 opened May 1, 2025 by achandrasekar
2
Summary and Per Request Report Generation
#56 opened Apr 25, 2025 by Bslabe123
2
[Feature] Per-request metrics CSV report
#55 opened Apr 25, 2025 by Bslabe123
Publish inference-perf image on GHCR
#52 opened Apr 21, 2025 by surajssd
Ephemeral Port Exhaustion
#50 opened Apr 10, 2025 by Bslabe123
Logger
#48 opened Mar 31, 2025 by Bslabe123
[Feature] CSV report for performance testing
#47 opened Mar 31, 2025 by SachinVarghese
3
Calculate Accurate Prompt Tokens for Chat Completions in vLLM Client
#45 opened Mar 31, 2025 by vivekk16
2
[Testing] Add test cases for validating inference perf load generation
#40 opened Mar 26, 2025 by SachinVarghese
[Feature] Improved error handling for LLM requests
#31 opened Mar 4, 2025 by SachinVarghese
[Feature] Collect Latency metrics - compute request time percentiles
#30 opened Mar 4, 2025 by SachinVarghese
[Feature] Define configuration for test runner
#26 opened Feb 20, 2025 by SachinVarghese
2
[Feature] Add a model server client for TGI
#24 opened Feb 20, 2025 by SachinVarghese
Consolidate perf testing tools
#23 opened Feb 19, 2025 by kfswain
9
Add Kubernetes Orchestration Library for Model Server Deployment and Benchmarking 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.
#22 opened Feb 13, 2025 by wangchen615
3
[Feature] Add a model server client for Triton using TensorRT-LLM lifecycle/stale Denotes an issue or PR has remained open with no activity and has become stale.
#18 opened Feb 3, 2025 by achandrasekar
1
[Feature] Add a client to get model server metrics lifecycle/stale Denotes an issue or PR has remained open with no activity and has become stale.
#17 opened Feb 3, 2025 by achandrasekar
1
[Feature] Add a load generator which sends a specific QPS
#16 opened Feb 3, 2025 by achandrasekar
1
[Feature] Support streaming requests with vLLM
#15 opened Feb 3, 2025 by achandrasekar
@Bslabe123
3
Proposal: Inference-perf loadgen component to be based on Grafana k6 load testing tool lifecycle/stale Denotes an issue or PR has remained open with no activity and has become stale.
#2 opened Jan 20, 2025 by SachinVarghese
10
ProTip! no:milestone will show everything without a milestone.