Skip to content

Pull requests: vllm-project/production-stack

New pull request New
80 Open 618 Closed
80 Open 618 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Doc][Bugfix] Use a Ray-capable image in the KubeRay tutorial
#1000 opened Jul 17, 2026 by cupkk Loading…
1
4
[Router][Bugfix] reset K8s watcher on stale resource version errors
#999 opened Jul 17, 2026 by loicrouillermonay Loading…
3
[Bugfix](router): strip Server header to avoid duplicate headers on response
#998 opened Jul 16, 2026 by mashun4ek Loading…
[Doc] Document disaggregated_prefill_orchestrated routingLogic option
#997 opened Jul 14, 2026 by Nicolas-Richard Loading…
3 tasks done
[Doc] Add priority routing proposal draft
#996 opened Jul 14, 2026 by punitvara Loading…
6
feat(operator): support shmSize on VLLMRuntime for tensor parallelism (#899)
#994 opened Jul 12, 2026 by Anai-Guo Contributor Loading…
1
4
fix(operator): use per-router names for VLLMRouter pod-viewer RBAC
#993 opened Jul 11, 2026 by Anai-Guo Contributor Loading…
1
3
[Feat][Helm] Support customizable resources and init containers for RayCluster
#992 opened Jul 7, 2026 by TheCodingSheikh Loading…
3 tasks done
7
[Bugfix][Router] Seed the prefix trie on the below-threshold QPS fallback path
#990 opened Jul 4, 2026 by vedcsolution Loading…
3
[Bugfix][Helm]: update Grafana dashboards to current vLLM metric names
#989 opened Jul 1, 2026 by bitnik Loading…
3 tasks done
5
feat(helm): support externally-managed PVC via pvcExistingClaimName (#938)
#988 opened Jul 1, 2026 by Anai-Guo Contributor Loading…
1
4
[Bugfix][Helm] skip lmcache dashboard when cache server is disabled
#987 opened Jul 1, 2026 by bitnik Loading…
3 tasks done
2
feat(helm/raySpec): allow customizing the Ray head node readiness probe (#742)
#986 opened Jul 1, 2026 by Anai-Guo Contributor Loading…
1
2
feat(router): support max_instance_failover_reroute_attempts in dynamic config
#984 opened Jun 30, 2026 by nejch Contributor • Draft
3 tasks
3
[Feat] Add timeouts to VLLM Router configuration
#983 opened Jun 30, 2026 by VariableDeclared Loading…
3 tasks done
1
2
feat(router): add --disable-access-log-for-endpoints to silence probe logs
#979 opened Jun 21, 2026 by Anai-Guo Contributor Loading…
1
3
feat: Bonsai Ternary 8B MIG deployment with LiteLLM proxy and Grafana…
#978 opened Jun 20, 2026 by markhembrow Loading…
3 tasks
7
[Build][Router] Bump lmcache to 0.4.7 and vllm to 0.22.0
#977 opened Jun 19, 2026 by zhengfeihe Loading…
9
[Feat][Router] Add per-algorithm routing decisions counter (Refs #474)
#951 opened May 13, 2026 by banlor Contributor Loading…
3 tasks done
5
[Bugfix] Fix /v1/audio/transcriptions endpoint when not using roundrobin
#950 opened May 12, 2026 by guba-elleschr Loading…
10
[BugFux] Fix help text formatting for Sentry sample rates in argument parser t…
#946 opened May 8, 2026 by xiaoajie738 Loading…
3 tasks
6
[Bugfix][Router] service_discovery: add has_ever_seen_model to K8sServiceNameServiceDiscovery
#945 opened May 8, 2026 by saikpr Loading…
3 tasks
10
[Feat][Router]: Add automatic retry with exponential backoff and jitter
#939 opened May 1, 2026 by ikaadil Contributor Loading…
8
[Feat][Router] Support multiple API keys for multi-tenant authentication (#759)
#937 opened Apr 29, 2026 by prashansapkota Contributor Loading…
1
8
fix(router): unify route_request to async with optional request_json
#929 opened Apr 23, 2026 by nejch Contributor Loading…
2 of 3 tasks
4
ProTip! Updated in the last three days: updated:>2026-07-16.