Commit Graph

23 Commits

Author SHA1 Message Date
Thomas Montfort efec27f9cf
feat: etcd-less operator updates (#4214) 2025-11-10 13:03:49 -08:00
Julien Mancuso a91e63482c
feat: add dynamoModel CRD (#4166)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2025-11-10 17:25:10 +00:00
Julien Mancuso 816a4c641f
fix: add PodClique watch to trigger DGD reconciliation (#4076)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2025-11-04 10:53:25 -07:00
Julien Mancuso bfbcae7aa8
fix: setup planner serviceaccount in cluster-wide deployment (#3520)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2025-10-09 14:22:01 -06:00
Michael Shin fcc42624a3
feat: Add vLLM compilation cache to Dynamo Operator (#3257)
Signed-off-by: Michael Shin <michaelshin@users.noreply.github.com>
2025-10-01 10:55:24 -04:00
Thomas Montfort 1a5016b035
feat: add subComponentType in DGD API and uptake in planner (#3200)
Signed-off-by: tmontfort <tmontfort@nvidia.com>
Signed-off-by: hongkuanz <hongkuanz@nvidia.com>
Co-authored-by: hongkuanz <hongkuanz@nvidia.com>
2025-09-29 09:40:58 -07:00
Julien Mancuso 37bc84444e
feat: add trtllm and vllm multinode k8s examples (#3100)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2025-09-23 15:18:44 -06:00
Julien Mancuso c3820050b9
feat: use official Grove 0.1.0-alpha release (#3030)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2025-09-15 14:55:51 -06:00
julienmancuso 9e6972a548
feat: Auto-inject kai-scheduler annotations and label (#2748)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2025-08-28 00:09:14 +00:00
julienmancuso 44ecfda539
fix: revisit grove and LWS selection (#2564)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2025-08-27 17:37:00 -06:00
julienmancuso 60a6a96aa3
fix: Reflect actual status of Grove PGS in Dynamo DGD (#2710)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2025-08-27 23:21:25 +00:00
julienmancuso a97602a2c9
fix: Implement scaling Grove subresources (#2531) 2025-08-19 18:54:22 +00:00
mohammedabdulwahhab 81c278038f
fix: operator defaults (#2398)
Signed-off-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
2025-08-14 16:05:12 -07:00
julienmancuso dabd226727
feat: add grove multinode support (#2269) 2025-08-11 14:31:02 -06:00
julienmancuso dbd33df6be
fix: handle groveTerminationDelay and auto-detect grove installation (#2190) 2025-07-31 18:18:24 -06:00
julienmancuso ee3a8e4283
feat: add initial Grove support (#2012) 2025-07-23 18:25:03 -06:00
julienmancuso 7a341f86f5
feat: simplify k8s deployment (#1708) 2025-07-08 00:29:26 +00:00
julienmancuso 51ca55278b
fix: take into account number of workers from config (#1365) 2025-06-04 12:42:05 -06:00
Rohan Varma 024422b9b0
feat: Add LWS to Dynamo Operator (#998)
Co-authored-by: Rohan Varma <rohanv@rohanv-mlt.client.nvidia.com>
Co-authored-by: Julien Mancuso <jmancuso@nvidia.com>
Co-authored-by: julienmancuso <161955438+julienmancuso@users.noreply.github.com>
2025-05-19 12:49:24 -06:00
julienmancuso e94f34443b
fix: read 'workers' to set deployments 'replicas' (#1040) 2025-05-13 20:00:00 -06:00
julienmancuso b2aa231704
feat: deploy planner in operator (#921)
Co-authored-by: mohammedabdulwahhab <furkhan324@berkeley.edu>
2025-05-08 17:32:31 -06:00
hhzhang16 1e8b286666
feat: add ingress to graph deployments (#960) 2025-05-07 23:04:15 -07:00
hhzhang16 403344e534
refactor: refactor dynamo deploy subfolder (#927) 2025-05-06 17:39:18 +00:00