Skip to content

Pull requests: vllm-project/production-stack

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
Reviews
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort

Pull requests list

[Feat] allow annotation on router pod
#743 opened Oct 30, 2025 by NargiT Loading…
3 tasks done
Bumping version to 0.1.8
#738 opened Oct 21, 2025 by YuhanLiu11 Loading…
3 tasks
[Bugfix] Added NULL check for session_key in KvawareRouter
#736 opened Oct 15, 2025 by vjayarag Loading…
3 tasks
[Bugfix] lmcache server points to wrong file in entrypoint
#730 opened Oct 9, 2025 by Senne-Mennes Loading…
3 tasks done
[Feat] Allow declaring modelSpec resources directly
#729 opened Oct 9, 2025 by danhubern Loading…
3 tasks done
[Feat][Router] Add HashTrie LRU to prevent OOM
#711 opened Sep 22, 2025 by can-sun Loading…
3 tasks done
[Bugfix][Router] use model_type instead of model_label
#705 opened Sep 19, 2025 by max-wittig Loading…
2 of 3 tasks
[Build] Update LMCache dependency to version 0.3.6
#701 opened Sep 17, 2025 by ikaadil Loading…
3 tasks
[Bugfix] kv aware routing for lmcache 0.3.5
#697 opened Sep 15, 2025 by zerofishnoodles Loading…
3 tasks done
feat: allow for configuration of number of uvicorn workers
#689 opened Sep 9, 2025 by TheCodeWrangler Loading…
8 tasks done
[Docs] Correct parameter in transcription API tutorial
#685 opened Sep 7, 2025 by davidgao7 Loading…
3 tasks done
[Bugfix] cache server yaml err
#677 opened Sep 4, 2025 by yyzxw Loading…
3 tasks done
[Feat][Router] Add TTFT Routing
#670 opened Sep 1, 2025 by chickeyton Draft
3 tasks
[Feat][PD] lastest PD support from LMCache with NIXL
#669 opened Aug 28, 2025 by kobe0938 Loading…
3 tasks
[Build] use uv with cache mount for faster docker builds
#657 opened Aug 23, 2025 by Hexoplon Loading…
3 tasks done
[Feat][Router] add ability to specify params to drop
#650 opened Aug 20, 2025 by max-wittig Loading…
3 tasks done
Add max_model_len field support to router
#638 opened Aug 11, 2025 by llm-net Loading…
ProTip! Filter pull requests by the default branch with base:main.