Commit Graph

56 Commits

Author SHA1 Message Date
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
MatejKosec 09b6ab2f74
fix(operator): shell-quote mpirun args + add nodeSelector to DGDR profilingConfig (#6248)
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
2026-02-13 15:12:58 -08:00
MatejKosec 6ef20625f7
fix(operator): fix SSH setup bugs in TRT-LLM multinode workers (#6225)
Signed-off-by: Matej Kosec <mkosec@nvidia.com>
2026-02-13 15:12:28 -08:00
Julien Mancuso 67883ec601
fix: omit nil/empty containers from ExtraPodSpec JSON to prevent CRD validation failure (#6255)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-13 15:33:25 -07:00
Thomas Montfort 0c83585a6f
fix: remove etcd key deletion logic from operator (#6263) 2026-02-13 10:16:47 -08:00
atchernych 5227176057
feat: Decomposed pipeline for EPP integration [DEP-730] (#5446)
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
2026-02-13 06:18:29 +00:00
Ashna Mehrotra a3f1e7ec62
fix: add DGD service name length validation (#5449)
Signed-off-by: ashnamehrotra <ashnamehrotra@gmail.com>
2026-02-12 19:19:47 +00:00
Hongkuan Zhou a04b56310c
feat: support AIC DGD gen call (WILL BREAK DGDR) (#6216)
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
2026-02-12 08:47:55 -08:00
dagil-nvidia 21abf07686
ci: fix fern CLI after docs/ migration by adding fern/ symlink (#6219)
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: Meenakshi Sharma <163925564+nvda-mesharma@users.noreply.github.com>
2026-02-11 17:19:49 -08:00
Jonathan Tong 39d645e586
docs: migrate Fern docs from fern/ into docs/ (#6206)
Signed-off-by: Jont828 <jt572@cornell.edu>
2026-02-11 16:22:27 -08:00
Schwinn Saereesitthipitak d381e6ff53
feat(chrek): config refactor, /dev/shm support, and mount-policy rewrite (#5946) 2026-02-12 00:09:00 +00:00
Julien Mancuso 4f686262de
feat: include operator version in DGD (#6121)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-11 12:19:55 -07:00
mohammedabdulwahhab d8628cc453
fix: fix cross selection issue amongst services in DGD (#6113)
Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
2026-02-10 11:03:53 -08:00
dagil-nvidia 3c9ca3fcb2
chore: add --no-install-recommends to apt-get install commands (#5774)
Signed-off-by: Dan Gil <dagil@nvidia.com>
Co-authored-by: Cursor <cursoragent@cursor.com>
2026-02-09 14:45:28 -06:00
Xavier Chang 410691dc97
fix: fix missing update DynamoComponentReady condition (#5051)
Signed-off-by: Xavier Chang <xuzhengc@nvidia.com>
2026-02-06 23:14:47 +00:00
Julien Mancuso d44fcde27c
feat: update grove dependency to 0.1.0-alpha.6 (#6015)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-06 12:35:42 -07:00
Julien Mancuso 94d82a485b
fix: correct restart state for parallel restarts (#5949)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
Co-authored-by: tmontfort <tmontfort@nvidia.com>
2026-02-04 20:22:18 +00:00
hhzhang16 0268aea4e3
fix: Add status file to prevent output-copier hang on failures (#5898)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-02-03 17:25:08 -08:00
Julien Mancuso f3aa1e0129
feat: introducing ChReK (Checkpoint Restore in K8s) (#4978)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-03 13:34:14 -07:00
atchernych 2d602853ed
feat: Add EPP startup probe and adjust recipe - fixes [DEP-749] (#5770)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
Co-authored-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-03 19:27:36 +00:00
ls-2018 96b6cb51ef
feat: remove useless branch condition (#4920)
Signed-off-by: acejilam <acejilam@gmail.com>
2026-01-30 08:04:32 -07:00
Julien Mancuso 9e2a2cc9e6
feat: add epp component (#5611)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-01-29 22:43:01 +00:00
Julien Mancuso 2b6d1338ca
fix(operator): correct structured logging in restart status tracking (#5800)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-01-29 20:46:59 +00:00
Jonathan Tong dd93d845c4
feat: add print columns with ready condition for v1alpha1 api types like DGD (#5542)
Signed-off-by: Jont828 <jt572@cornell.edu>
2026-01-28 15:56:19 -06:00
hhzhang16 7d3c67f081
feat: use consts instead of hardcoded string for statuses (#5696)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-01-28 13:04:58 -08:00
Julien Mancuso 53a609e538
feat: add dynamo operator observability (#5543)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-01-22 15:48:28 -07:00
Neelay Shah 283b20c961
fix: apply labels to Kubernetes Service objects in operator (#5459)
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-15 11:54:34 -08:00
hhzhang16 c8770464ab
feat: normalize dynamo namespace computation (#5231)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-01-12 19:09:43 +00:00
hhzhang16 ec5630ead9
feat: mount model path to Profiler if specified (#5212)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-01-09 17:13:53 +00:00
Thomas Montfort 3d67474ef3
feat(operator): DynamoGraphDeployment rollout restart mechanism (#5118) 2026-01-08 15:25:13 -08:00
Julien Mancuso 55c2665452
fix: prevent services adding/removal in dgd (#5240)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-01-08 06:59:44 -07:00