Commit Graph

86 Commits

Author SHA1 Message Date
devivasudevan 57648c1961
feat: GPU discovery extension using DCGM exporter for advanced metrics. (#6705)
Signed-off-by: devivasudevan <49675305+devivasudevan@users.noreply.github.com>
2026-03-13 07:51:59 -07:00
dependabot[bot] 82f60cc781
build(deps): bump go.opentelemetry.io/otel/sdk from 1.38.0 to 1.40.0 in /deploy/operator (#7242)
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Dmitry Tokarev <dtokarev@nvidia.com>
2026-03-11 18:04:06 -04:00
Raghav Potluri a31cbd0df9
fix(operator): prevent nil pointer panic when DGD service omits replicas (#6739)
Signed-off-by: Raghav Potluri <raghav.potluri21@gmail.com>
2026-03-10 22:26:50 -07:00
hhzhang16 611e856d87
feat: hide optimizationType (#7160)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-03-11 00:36:18 +00:00
hhzhang16 fce90859b9
fix: populate profilingResults, clear profilingPhase, and update Profiling condition after profiling completes (#7116)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-03-10 18:35:46 -05:00
hhzhang16 0d5df9f671
fix: allow x-kubernetes-preserve-unknown-fields (#7128)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-03-09 19:47:08 -07:00
hhzhang16 8f3188d3e2
feat: add missing overrides (#7017)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-03-09 14:59:07 -07:00
hhzhang16 71f9e7a9de
fix: normalize GPUSKU to AIC system identifier (#6984)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-03-09 12:58:39 -05:00
Schwinn Saereesitthipitak 6831020f35
chore: rename chrek to Dynamo Snapshot (#7028)
Signed-off-by: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com>
2026-03-08 15:13:36 -04:00
Thomas Montfort 7dbebf3c61
refactor: replace kube-rbac-proxy sidecar with controller-runtime WithAuthenticationAndAuthorization (#7045) 2026-03-07 08:01:03 -08:00
hhzhang16 f1dbea4f20
fix: sanitize dots in DGD names for DNS-1035 and dynamo namespace endpoint paths (#7032)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-03-07 01:23:58 +00:00
Julien Mancuso fc2d01d111
refactor: move MPI SSH key generation from Helm hook Job into operator reconciliation (#6940)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-03-06 18:25:00 +00:00
hhzhang16 b97fde10f9
fix: propagate tolerations and cap auto-discovered GPUs (#6947)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-03-06 00:33:19 +00:00
Julien Mancuso 7f1f3076a6
fix: fix operator race condition (#6929)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-03-05 08:31:53 -08:00
Julien Mancuso e43b30506c
feat: move webhook certificate management and CA injection from Helm hooks into the operator (#6839)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-03-04 14:12:29 -08:00
atchernych 73a4ab3172
chore: Optimizations for epp interface complience (#6581)
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
2026-03-04 03:46:04 +00:00
hhzhang16 e460181157
feat: use model_fields_set to distinguish ttft/itl default usage (#6814)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-03-03 11:32:04 -08:00
Julien Mancuso 0404a9be29
fix: allow v1alpha1 DGDR creation by fixing webhook version matching and backend enum (#6803)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-03-03 10:17:25 -07:00
Neal Vaidya ece08dc926
docs: restructure docs directory and move fern config to fern/ (#6700)
Signed-off-by: Neal Vaidya <nealv@nvidia.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-01 19:58:22 -08:00
MatejKosec d152596af2
fix(operator): fix TRT-LLM worker SSH crash in non-root containers (#6694)
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
2026-02-28 02:02:57 +00:00
Julien Mancuso dba51eed82
fix: propagate vllm-distributed-executor-backend annotation from DGD metadata to backends (#6692)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-27 16:07:11 -07:00
hhzhang16 98a6d3b910
fix: store nodesWithGPUs (#6690)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-02-27 22:52:17 +00:00
hhzhang16 35c3049366
fix: AutoApply bool --> AutoApply *bool (#6683)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-02-27 14:38:00 -08:00
Julien Mancuso 880db75d67
fix: shell-quote Ray leader args (#6693)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-27 15:34:57 -07:00
Ashna Mehrotra d8b7d394ac
docs: V1beta1 dgdr docs (#6647)
Signed-off-by: ashnamehrotra <ashnamehrotra@gmail.com>
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-02-27 22:33:11 +00:00
Julien Mancuso ab01462a03
feat: add profiler job overrides (#6607)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-26 13:08:48 -07:00
Harrison Saturley-Hall db88c9530b
chore: bump versions to 1.0.0 (#6613)
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
2026-02-25 22:42:33 -05:00
hhzhang16 06fc5d5ecf
feat: Make the image field optional in DGDRs (#6557)
Signed-off-by: Jont828 <jt572@cornell.edu>
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: Jont828 <jt572@cornell.edu>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Hongkuan Zhou <tedzhouhk@gmail.com>
2026-02-25 17:27:57 -08:00
Hongkuan Zhou 4c648b11e9
refactor: move core logics of DPP -> AIC and support static profiling (#6285)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Co-authored-by: hhzhang16 <54051230+hhzhang16@users.noreply.github.com>
2026-02-26 00:39:50 +00:00
Jonathan Tong d100c6e200
feat: use v1beta1 DGDR in controller (#6498)
Signed-off-by: Jont828 <jt572@cornell.edu>
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Hannah Zhang <hannahz@nvidia.com>
2026-02-25 18:28:16 -06:00
Pavithra Vijayakrishnan 5734f5c427
chore: Update the reference in readme (#6298)
Signed-off-by: pvijayakrish <pvijayakrish@nvidia.com>
2026-02-25 08:56:07 +00:00
atchernych c916cd42ff
feat: Support epp's "pods" interface in Dynamo fixes [DEP-424] (#6302)
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
2026-02-25 01:54:38 +00:00
Julien Mancuso fcdf661009
chore: document all env vars injected by operator (#6548)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-24 15:59:39 -07:00
Thomas Montfort c0f34b15a0
feat(operator): operator config versioning and injected as configmap (#6464) 2026-02-24 10:26:28 -08:00
hhzhang16 659122ed07
feat: add Planner schema to DGDR and Profiler input (#6463)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Co-authored-by: Sertaç Özercan <852750+sozercan@users.noreply.github.com>
2026-02-24 10:14:57 -05:00
Julien Mancuso 5277fb9bbe
feat: simplify CRD management (#6466)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-23 19:18:13 -07:00
Julien Mancuso 8dd6369e55
feat: use vllm multiprocessing in multinode scenario (#6191)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-23 22:30:34 +00:00
Schwinn Saereesitthipitak bb8fc8a4a9
feat(chrek): external restore, signal-based IPC, and package refactor (#6286)
Co-authored-by: Dan Feigin <dfeigin@nvidia.com>
2026-02-21 01:31:32 +00:00
Julien Mancuso fd839b8d57
fix: reintroduce helm docs autogeneration (#6459)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-20 14:33:15 -07:00
Julien Mancuso f385661ae0
chore: remove mechanism to disable webhooks (#6441)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-20 09:53:10 -07:00
hhzhang16 ebc61637d8
feat: Add v1beta1 DGDR API with conversion framework (#6352)
Signed-off-by: Jont828 <jt572@cornell.edu>
Signed-off-by: Hongkuan Zhou <hongkuanz@nvidia.com>
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
Co-authored-by: Jont828 <jt572@cornell.edu>
2026-02-19 23:09:02 -08:00
Julien Mancuso dad4237dce
chore: remove DCD debug features and consolidate k8s service generation (#6397)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-19 19:38:24 +00:00
Thomas Montfort 61889a14fb
feat(operator): add observedGeneration to DGD status (#6398) 2026-02-18 19:08:50 -08:00
hhzhang16 6a3f2002bd
feat: Optional GPU Discovery for Namespace-Scoped Operators (#6343)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-02-18 18:13:06 -08:00
Thomas Montfort 72579ee7d8
feat: add DGDR Status .state enum (#6396) 2026-02-18 22:55:27 +00:00
Thomas Montfort 7fb9582569
fix(ci): operator CI (#6390) 2026-02-18 13:58:11 -08:00
Nikita 82f721c738
feat: Add DGD .status.state enum (#6324)
Signed-off-by: Nikita Sukharev <kaonael@gmail.com>
2026-02-18 14:53:06 -06:00
Thomas Montfort 97f795377b
feat(operator): managed rolling updates for DGD worker deployments (#6110)
Signed-off-by: tmontfort <tmontfort@nvidia.com>
2026-02-17 09:23:00 -08:00
alexanderbilk 9200ac9b30
feat: Added NIXL Telemetry prometheus port (#5567)
Signed-off-by: Aleksandr Bilkovskii <alexanderb@nvidia.com>
2026-02-15 17:14:56 +02:00
hhzhang16 d56439ec28
feat: migrate GPU discovery from Dynamo Profiler to Dynamo Operator with automatic injection (#6224)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-02-14 00:34:21 +00:00