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
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
92b341f36e
docs: update snapshot checkpointing docs ( #7244 )
2026-03-11 22:00:24 +00:00
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
611e856d87
feat: hide optimizationType ( #7160 )
...
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-03-11 00:36:18 +00:00
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
734c0b8b0b
feat: Add Loki log aggregation, and enable unified OTLP ingestion for both traces and logs through a single endpoint ( #6974 )
2026-03-10 15:20:33 -07:00
3c44b88e89
feat(perf): add frontend pipeline and tokio runtime perf metric definitions ( #6731 )
2026-03-10 21:04:02 +00:00
419e936a53
refactor: remove benchmark shim, use AIPerf directly ( #7074 )
...
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>
2026-03-10 03:41:36 +00:00
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
8481236c82
docs: correct dead kvstats metric names in Grafana dashboards and docs ( #7123 )
...
Signed-off-by: Keiven Chang <keivenchang@users.noreply.github.com>
Co-authored-by: Keiven Chang <keivenchang@users.noreply.github.com>
2026-03-09 18:21:31 -07:00
3a09a559ff
fix: make snapshot CI image linter pass ( #7124 )
2026-03-10 01:09:43 +00:00
8f3188d3e2
feat: add missing overrides ( #7017 )
...
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-03-09 14:59:07 -07:00
d54af4f8cf
chore: restrict Dynamo Snapshot to x86_64, document backend support ( #7031 )
2026-03-09 14:14:39 -07:00
b5fddbd009
fix(helm): remove metrics-reader ClusterRole ( #7107 )
2026-03-09 21:04:49 +00:00
f5b1cb4775
fix: Add Env support to operator Helm chart deployment values ( #7081 )
...
Signed-off-by: qasmi <qasmisara@gmail.com>
2026-03-09 12:41:11 -07:00
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
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
7dbebf3c61
refactor: replace kube-rbac-proxy sidecar with controller-runtime WithAuthenticationAndAuthorization ( #7045 )
2026-03-07 08:01:03 -08:00
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
28f089d81a
fix: remove outdated deploy/discovery example ( #7000 )
...
Signed-off-by: Dan Gil <dagil@nvidia.com>
2026-03-06 12:35:47 -08:00
d882892012
chore: align EPP Rust image to 1.93.1 ( #7003 )
2026-03-06 12:34:46 -08:00
b07be71b20
fix(chrek): pass checkpointPath to restore ( #6941 )
2026-03-06 18:29:16 +00:00
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
f934744fb9
fix: restore --enforce-disagg to reject requests before prefill router activates ( #6957 )
...
Signed-off-by: PeaBrane <yanrpei@gmail.com>
2026-03-06 04:39:28 +00:00
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
7f1f3076a6
fix: fix operator race condition ( #6929 )
...
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-03-05 08:31:53 -08:00
3c0fdd050f
chore: bump(deploy): go otel sdk to v1.40.0 ( #6901 )
2026-03-04 14:33:38 -08:00
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
73a4ab3172
chore: Optimizations for epp interface complience ( #6581 )
...
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
2026-03-04 03:46:04 +00:00
a01cd9c19d
refactor: move CRD apply from Helm hook Job to init container on operator Deployment ( #6780 )
...
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-03-03 17:42:45 -07:00
9254e3d4d2
chore: update nixl version to 0.10.1 ( #6826 )
...
Signed-off-by: Anant Sharma <anants@nvidia.com>
2026-03-03 16:47:55 -05:00
2ff744047a
fix: update nixl version to 0.10.0 ( #6789 )
2026-03-03 15:14:42 -05:00
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
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
93fa4d4d01
chore: update version and repo of chrek helm chart ( #6738 )
...
Signed-off-by: Harrison Saturley-Hall <hsaturleyhal@nvidia.com>
2026-03-02 17:15:12 -05:00
ee33acf3c3
fix: Add weight: 1 to the EPP config plugins ( #6756 )
...
Signed-off-by: Anna Tchernych <atchernych@nvidia.com>
2026-03-02 22:13:44 +00:00
17693cf8a9
fix: autogenerate helm chart readme ( #6774 )
...
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-03-02 15:08:43 -07:00
f83d9a532f
fix: decouple Helm chart from runtime cluster state for helm template and GitOps compatibility ( #6754 )
...
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-03-02 14:19:14 -07:00
72eabeae14
fix: always emit pvc block in operator configmap when checkpoint storage type is pvc ( #6752 )
...
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-03-02 09:44:34 -07:00
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
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
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
98a6d3b910
fix: store nodesWithGPUs ( #6690 )
...
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-02-27 22:52:17 +00:00
35c3049366
fix: AutoApply bool --> AutoApply *bool ( #6683 )
...
Signed-off-by: Hannah Zhang <hannahz@nvidia.com>
2026-02-27 14:38:00 -08:00
880db75d67
fix: shell-quote Ray leader args ( #6693 )
...
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-27 15:34:57 -07:00
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
f1d5c95a4e
feat: wire nvext.cache_control TTL-based pinning through Dynamo router ( #6213 )
...
Co-authored-by: Claude <noreply@anthropic.com>
2026-02-27 01:03:27 +00:00
ab01462a03
feat: add profiler job overrides ( #6607 )
...
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-26 13:08:48 -07:00
2b077ec22c
fix: fix gpu discovery preflight job ( #6628 )
...
Signed-off-by: Julien Mancuso <jmancuso@nvidia.com>
2026-02-26 13:02:19 -07:00
devivasudevan