-
Notifications
You must be signed in to change notification settings - Fork 487
Pull requests: vllm-project/production-stack
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
[Bugfix] Keep multi-round benchmark summaries consistent
#1090
opened Sep 14, 2026 by
1fanwang
Loading…
3 of 4 tasks
[Bugfix][Router] Use least-inflight for PrefixAware below-threshold fallback
#1089
opened Sep 13, 2026 by
dundysm
Contributor
Loading…
3 tasks done
[Feat] Opt-in DRA allocation mode per model
#1086
opened Sep 13, 2026 by
jdubs
Loading…
3 tasks done
[CI/Build] Use mock backends for static-discovery e2e (part of #531)
#1085
opened Sep 13, 2026 by
ighutake-debug
Contributor
Loading…
2 tasks done
[Bugfix][Router] Validate static service discovery list lengths
#1084
opened Sep 11, 2026 by
Alex-Wengg
Loading…
3 tasks done
[Router] Make backend request timeouts configurable via environment variables
#1082
opened Sep 10, 2026 by
vitush93
Loading…
[Helm][Feature] Add vllm-stack-operator chart: operator, CRDs and CRs in one helm install
#1081
opened Sep 10, 2026 by
jackiesre721
Loading…
[Bugfix][Router] Use supplied timestamp for avg_latency and drop completed request maps
#1080
opened Sep 7, 2026 by
nisaral
Loading…
[Operator] Add separate resource requests and limits
#1079
opened Sep 3, 2026 by
banlor
Contributor
Loading…
[Router][Bugfix] Log a warning when an engine scrape matches zero known metric names
#1076
opened Sep 2, 2026 by
pujitha24
Loading…
3 tasks done
[Router][Bugfix] Decouple the engine-stats read timeout from the scrape interval
#1075
opened Sep 2, 2026 by
sethforprivacy
Loading…
3 tasks done
[Bugfix][Router] Fix leaked in-flight counters in RequestStatsMonitor
#1072
opened Sep 2, 2026 by
lfsun02
Contributor
Loading…
3 tasks done
[Feat] Support command and args on servingEngineSpec.modelSpec
#1071
opened Sep 1, 2026 by
dundysm
Contributor
Loading…
2 of 3 tasks
[Bugfix][Router] Run KvawareRouter /tokenize fallback in executor to avoid blocking event loop
#1069
opened Aug 29, 2026 by
Asthenia0412
Loading…
[Bugfix][Helm] Only pass --k8s-service-discovery-type when explicitly set to non-default
#1068
opened Aug 29, 2026 by
Asthenia0412
Loading…
fix: Improve JSON parsing robustness under high concurrency
#1067
opened Aug 29, 2026 by
Asthenia0412
Loading…
fix: Use per-model tokenizer in KvawareRouter for multi-model setups
#1066
opened Aug 29, 2026 by
Asthenia0412
Loading…
fix: Replace exec liveness probe with tcpSocket for LMCache cache server
#1065
opened Aug 29, 2026 by
Asthenia0412
Loading…
fix: Use broad except clause for k8s config loading to avoid TypeError
#1064
opened Aug 29, 2026 by
Asthenia0412
Loading…
fix: Add OpenAPI request body schema to all POST routes for Swagger UI
#1063
opened Aug 29, 2026 by
Asthenia0412
Loading…
3 tasks
[Doc] Tutorial 17: troubleshooting the silent-miss preconditions of kvaware routing
#1062
opened Aug 29, 2026 by
tyler2cr
Loading…
[Router][Bugfix] Defensive fallbacks in kvaware routing: 503 on no endpoints, session/QPS on unmapped instance
#1061
opened Aug 29, 2026 by
tyler2cr
Loading…
[CI/Build][Router] Enable lmcache 0.5.4 for the kvaware router stack
#1060
opened Aug 28, 2026 by
tyler2cr
Loading…
[Bugfix] Use TCP liveness probe for LMCache server
#1058
opened Aug 27, 2026 by
EltonChang1
•
Draft
3 tasks done
[Bugfix][Router] Update average decoding duration stats
#1054
opened Aug 25, 2026 by
dsxyy
Contributor
Loading…
Previous Next
ProTip!
Adding no:label will show everything without a label.