Commits · 57648c196130c7281de48412c5b8f71f7005ef1a · OpenDAS / dynamo · GitLab

13 Mar, 2026 1 commit
- feat: GPU discovery extension using DCGM exporter for advanced metrics. (#6705) · 57648c19
  devivasudevan authored Mar 13, 2026
```
Signed-off-by: devivasudevan <49675305+devivasudevan@users.noreply.github.com>
```
  57648c19
11 Mar, 2026 4 commits
- build(deps): bump go.opentelemetry.io/otel/sdk from 1.38.0 to 1.40.0 in /deploy/operator (#7242) · 82f60cc7
  dependabot[bot] authored Mar 11, 2026
```
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>
```
  82f60cc7
- docs: update snapshot checkpointing docs (#7244) · 92b341f3
  Schwinn Saereesitthipitak authored Mar 11, 2026
  
  92b341f3
- fix(operator): prevent nil pointer panic when DGD service omits replicas (#6739) · a31cbd0d
  Raghav Potluri authored Mar 10, 2026
```
Signed-off-by: Raghav Potluri <raghav.potluri21@gmail.com>
```
  a31cbd0d
- feat: hide optimizationType (#7160) · 611e856d
  hhzhang16 authored Mar 10, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  611e856d
10 Mar, 2026 7 commits
- fix: populate profilingResults, clear profilingPhase, and update Profiling... · fce90859
  hhzhang16 authored Mar 10, 2026
```
fix: populate profilingResults, clear profilingPhase, and update Profiling condition after profiling completes (#7116)
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  fce90859
- feat: Add Loki log aggregation, and enable unified OTLP ingestion for both... · 734c0b8b
  jh-nv authored Mar 10, 2026
```
feat: Add Loki log aggregation, and enable unified OTLP ingestion for both traces and logs through a single endpoint (#6974)
```
  734c0b8b
- feat(perf): add frontend pipeline and tokio runtime perf metric definitions (#6731) · 3c44b88e
  Biswa Panda authored Mar 10, 2026
  
  3c44b88e
- refactor: remove benchmark shim, use AIPerf directly (#7074) · 419e936a
  Ben Hamm authored Mar 09, 2026
```
Signed-off-by: Ben Hamm <ben.hamm@gmail.com>
Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Biswa Panda <biswa.panda@gmail.com>
Co-authored-by: Saravana Periyasamy <saperiyasamy@nvidia.com>
```
  419e936a
- fix: allow x-kubernetes-preserve-unknown-fields (#7128) · 0d5df9f6
  hhzhang16 authored Mar 09, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  0d5df9f6
- docs: correct dead kvstats metric names in Grafana dashboards and docs (#7123) · 8481236c
  Keiven C authored Mar 09, 2026
```
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
```
  8481236c
- fix: make snapshot CI image linter pass (#7124) · 3a09a559
  Schwinn Saereesitthipitak authored Mar 09, 2026
  
  3a09a559
09 Mar, 2026 5 commits
- feat: add missing overrides (#7017) · 8f3188d3
  hhzhang16 authored Mar 09, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  8f3188d3
- chore: restrict Dynamo Snapshot to x86_64, document backend support (#7031) · d54af4f8
  Schwinn Saereesitthipitak authored Mar 09, 2026
  
  d54af4f8
- fix(helm): remove metrics-reader ClusterRole (#7107) · b5fddbd0
  Thomas Montfort authored Mar 09, 2026
  
  b5fddbd0
- fix: Add Env support to operator Helm chart deployment values (#7081) · f5b1cb47
  sara authored Mar 09, 2026
```
Signed-off-by: qasmi <qasmisara@gmail.com>
```
  f5b1cb47
- fix: normalize GPUSKU to AIC system identifier (#6984) · 71f9e7a9
  hhzhang16 authored Mar 09, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  71f9e7a9
08 Mar, 2026 1 commit
- chore: rename chrek to Dynamo Snapshot (#7028) · 6831020f
  Schwinn Saereesitthipitak authored Mar 08, 2026
```
Signed-off-by: Schwinn Saereesitthipitak <17022745+galletas1712@users.noreply.github.com>
```
  6831020f
07 Mar, 2026 2 commits
- refactor: replace kube-rbac-proxy sidecar with controller-runtime... · 7dbebf3c
  Thomas Montfort authored Mar 07, 2026
```
refactor: replace kube-rbac-proxy sidecar with controller-runtime WithAuthenticationAndAuthorization (#7045)
```
  7dbebf3c
- fix: sanitize dots in DGD names for DNS-1035 and dynamo namespace endpoint paths (#7032) · f1dbea4f
  hhzhang16 authored Mar 06, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  f1dbea4f
06 Mar, 2026 6 commits
- fix: remove outdated deploy/discovery example (#7000) · 28f089d8
  dagil-nvidia authored Mar 06, 2026
```
Signed-off-by: Dan Gil <dagil@nvidia.com>
```
  28f089d8
- chore: align EPP Rust image to 1.93.1 (#7003) · d8828920
  Anant Sharma authored Mar 06, 2026
  
  d8828920
- fix(chrek): pass checkpointPath to restore (#6941) · b07be71b
  Janelle Cai authored Mar 06, 2026
  
  b07be71b
- refactor: move MPI SSH key generation from Helm hook Job into operator reconciliation (#6940) · fc2d01d1
  Julien Mancuso authored Mar 06, 2026
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  fc2d01d1
- fix: restore --enforce-disagg to reject requests before prefill router activates (#6957) · f934744f
  Yan Ru Pei authored Mar 05, 2026
```
Signed-off-by: PeaBrane <yanrpei@gmail.com>
```
  f934744f
- fix: propagate tolerations and cap auto-discovered GPUs (#6947) · b97fde10
  hhzhang16 authored Mar 05, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  b97fde10
05 Mar, 2026 1 commit
- fix: fix operator race condition (#6929) · 7f1f3076
  Julien Mancuso authored Mar 05, 2026
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  7f1f3076
04 Mar, 2026 4 commits
- chore: bump(deploy): go otel sdk to v1.40.0 (#6901) · 3c0fdd05
  Thomas Montfort authored Mar 04, 2026
  
  3c0fdd05
- feat: move webhook certificate management and CA injection from Helm hooks... · e43b3050
  Julien Mancuso authored Mar 04, 2026
```
feat: move webhook certificate management and CA injection from Helm hooks into the operator (#6839)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  e43b3050
- chore: Optimizations for epp interface complience (#6581) · 73a4ab31
  atchernych authored Mar 03, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  73a4ab31
- refactor: move CRD apply from Helm hook Job to init container on operator Deployment (#6780) · a01cd9c1
  Julien Mancuso authored Mar 03, 2026
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  a01cd9c1
03 Mar, 2026 4 commits
- chore: update nixl version to 0.10.1 (#6826) · 9254e3d4
  Anant Sharma authored Mar 03, 2026
```
Signed-off-by: Anant Sharma <anants@nvidia.com>
```
  9254e3d4
- fix: update nixl version to 0.10.0 (#6789) · 2ff74404
  Biswa Panda authored Mar 03, 2026
  
  2ff74404
- feat: use model_fields_set to distinguish ttft/itl default usage (#6814) · e4601811
  hhzhang16 authored Mar 03, 2026
```
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
```
  e4601811
- fix: allow v1alpha1 DGDR creation by fixing webhook version matching and backend enum (#6803) · 0404a9be
  Julien Mancuso authored Mar 03, 2026
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  0404a9be
02 Mar, 2026 5 commits
- chore: update version and repo of chrek helm chart (#6738) · 93fa4d4d
  Harrison Saturley-Hall authored Mar 02, 2026
```
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
```
  93fa4d4d
- fix: Add weight: 1 to the EPP config plugins (#6756) · ee33acf3
  atchernych authored Mar 02, 2026
```
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
```
  ee33acf3
- fix: autogenerate helm chart readme (#6774) · 17693cf8
  Julien Mancuso authored Mar 02, 2026
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  17693cf8
- fix: decouple Helm chart from runtime cluster state for helm template and... · f83d9a53
  Julien Mancuso authored Mar 02, 2026
```
fix: decouple Helm chart from runtime cluster state for helm template and GitOps compatibility (#6754)
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  f83d9a53
- fix: always emit pvc block in operator configmap when checkpoint storage type is pvc (#6752) · 72eabeae
  Julien Mancuso authored Mar 02, 2026
```
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
```
  72eabeae