From 37ddb8b1195979202c64777803ed2b17925ce933 Mon Sep 17 00:00:00 2001 From: Samarth Singh <45368705+sam6134@users.noreply.github.com> Date: Thu, 9 May 2024 13:16:34 +0100 Subject: [PATCH 1/4] Add Sagemaker instances to node-affinity --- charts/amazon-cloudwatch-observability/values.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/charts/amazon-cloudwatch-observability/values.yaml b/charts/amazon-cloudwatch-observability/values.yaml index 27849f0..0c23ff9 100644 --- a/charts/amazon-cloudwatch-observability/values.yaml +++ b/charts/amazon-cloudwatch-observability/values.yaml @@ -19,10 +19,10 @@ region: nodeLabelKey: node.kubernetes.io/instance-type ## NVIDIA GPU instance types -gpuInstances: [ p2.xlarge, p2.8xlarge, p2.16xlarge, p3.2xlarge, p3.8xlarge, p3.16xlarge, p3dn.24xlarge, p4d.24xlarge, p4de.24xlarge, p5.48xlarge, g3s.xlarge, g3.4xlarge, g3.8xlarge, g3.16xlarge, g4dn.xlarge, g4dn.2xlarge, g4dn.4xlarge, g4dn.8xlarge, g4dn.16xlarge, g4dn.12xlarge, g4dn.metal, g4ad.xlarge, g4ad.2xlarge, g4ad.4xlarge, g4ad.8xlarge, g4ad.16xlarge, g5.xlarge, g5.2xlarge, g5.4xlarge, g5.8xlarge, g5.16xlarge, g5.12xlarge, g5.24xlarge, g5.48xlarge, g5g.xlarge, g5g.2xlarge, g5g.4xlarge, g5g.8xlarge, g5g.16xlarge, g5g.metal ] +gpuInstances: [ p2.xlarge, p2.8xlarge, p2.16xlarge, p3.2xlarge, p3.8xlarge, p3.16xlarge, p3dn.24xlarge, p4d.24xlarge, p4de.24xlarge, p5.48xlarge, g3s.xlarge, g3.4xlarge, g3.8xlarge, g3.16xlarge, g4dn.xlarge, g4dn.2xlarge, g4dn.4xlarge, g4dn.8xlarge, g4dn.16xlarge, g4dn.12xlarge, g4dn.metal, g4ad.xlarge, g4ad.2xlarge, g4ad.4xlarge, g4ad.8xlarge, g4ad.16xlarge, g5.xlarge, g5.2xlarge, g5.4xlarge, g5.8xlarge, g5.16xlarge, g5.12xlarge, g5.24xlarge, g5.48xlarge, g5g.xlarge, g5g.2xlarge, g5g.4xlarge, g5g.8xlarge, g5g.16xlarge, g5g.metal, ml.p5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.p3dn.24xlarge , ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.16xlarge, ml.g4dn.12xlarge, ml.g5n.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge] ## Tranium/Infrentia instance types -neuronInstances: [ trn1.2xlarge, trn1.32xlarge, trn1n.32xlarge, inf1.xlarge, inf1.2xlarge, inf1.6xlarge, inf1.24xlarge, inf2.xlarge, inf2.8xlarge, inf2.24xlarge, inf2.48xlarge ] +neuronInstances: [ trn1.2xlarge, trn1.32xlarge, trn1n.32xlarge, inf1.xlarge, inf1.2xlarge, inf1.6xlarge, inf1.24xlarge, inf2.xlarge, inf2.8xlarge, inf2.24xlarge, inf2.48xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.inf1.xlarge, ml.inf1.2xlarge, ml.inf1.6xlarge, ml.inf1.24xlarge, ml.inf2.xlarge, ml.inf2.8xlarge, ml.inf2.24xlarge, ml.inf2.48xlarge] containerLogs: enabled: true From 4bb9da77650ae9d81b8a94cb8a56609c16080e59 Mon Sep 17 00:00:00 2001 From: Samarth Singh <45368705+sam6134@users.noreply.github.com> Date: Thu, 9 May 2024 15:34:16 +0100 Subject: [PATCH 2/4] Add ml.trn1n.32xlarge --- charts/amazon-cloudwatch-observability/values.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/charts/amazon-cloudwatch-observability/values.yaml b/charts/amazon-cloudwatch-observability/values.yaml index 0c23ff9..10a7458 100644 --- a/charts/amazon-cloudwatch-observability/values.yaml +++ b/charts/amazon-cloudwatch-observability/values.yaml @@ -22,7 +22,7 @@ nodeLabelKey: node.kubernetes.io/instance-type gpuInstances: [ p2.xlarge, p2.8xlarge, p2.16xlarge, p3.2xlarge, p3.8xlarge, p3.16xlarge, p3dn.24xlarge, p4d.24xlarge, p4de.24xlarge, p5.48xlarge, g3s.xlarge, g3.4xlarge, g3.8xlarge, g3.16xlarge, g4dn.xlarge, g4dn.2xlarge, g4dn.4xlarge, g4dn.8xlarge, g4dn.16xlarge, g4dn.12xlarge, g4dn.metal, g4ad.xlarge, g4ad.2xlarge, g4ad.4xlarge, g4ad.8xlarge, g4ad.16xlarge, g5.xlarge, g5.2xlarge, g5.4xlarge, g5.8xlarge, g5.16xlarge, g5.12xlarge, g5.24xlarge, g5.48xlarge, g5g.xlarge, g5g.2xlarge, g5g.4xlarge, g5g.8xlarge, g5g.16xlarge, g5g.metal, ml.p5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.p3dn.24xlarge , ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.16xlarge, ml.g4dn.12xlarge, ml.g5n.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge] ## Tranium/Infrentia instance types -neuronInstances: [ trn1.2xlarge, trn1.32xlarge, trn1n.32xlarge, inf1.xlarge, inf1.2xlarge, inf1.6xlarge, inf1.24xlarge, inf2.xlarge, inf2.8xlarge, inf2.24xlarge, inf2.48xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.inf1.xlarge, ml.inf1.2xlarge, ml.inf1.6xlarge, ml.inf1.24xlarge, ml.inf2.xlarge, ml.inf2.8xlarge, ml.inf2.24xlarge, ml.inf2.48xlarge] +neuronInstances: [ trn1.2xlarge, trn1.32xlarge, trn1n.32xlarge, inf1.xlarge, inf1.2xlarge, inf1.6xlarge, inf1.24xlarge, inf2.xlarge, inf2.8xlarge, inf2.24xlarge, inf2.48xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge, ml.inf1.xlarge, ml.inf1.2xlarge, ml.inf1.6xlarge, ml.inf1.24xlarge, ml.inf2.xlarge, ml.inf2.8xlarge, ml.inf2.24xlarge, ml.inf2.48xlarge] containerLogs: enabled: true From 8f3695543afd52cc87b6265207a75beb657f0b7f Mon Sep 17 00:00:00 2001 From: Samarth Singh <45368705+sam6134@users.noreply.github.com> Date: Fri, 10 May 2024 14:46:34 +0100 Subject: [PATCH 3/4] Add all original instances with ml prefixes --- charts/amazon-cloudwatch-observability/values.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/charts/amazon-cloudwatch-observability/values.yaml b/charts/amazon-cloudwatch-observability/values.yaml index 10a7458..d8b64ac 100644 --- a/charts/amazon-cloudwatch-observability/values.yaml +++ b/charts/amazon-cloudwatch-observability/values.yaml @@ -19,7 +19,7 @@ region: nodeLabelKey: node.kubernetes.io/instance-type ## NVIDIA GPU instance types -gpuInstances: [ p2.xlarge, p2.8xlarge, p2.16xlarge, p3.2xlarge, p3.8xlarge, p3.16xlarge, p3dn.24xlarge, p4d.24xlarge, p4de.24xlarge, p5.48xlarge, g3s.xlarge, g3.4xlarge, g3.8xlarge, g3.16xlarge, g4dn.xlarge, g4dn.2xlarge, g4dn.4xlarge, g4dn.8xlarge, g4dn.16xlarge, g4dn.12xlarge, g4dn.metal, g4ad.xlarge, g4ad.2xlarge, g4ad.4xlarge, g4ad.8xlarge, g4ad.16xlarge, g5.xlarge, g5.2xlarge, g5.4xlarge, g5.8xlarge, g5.16xlarge, g5.12xlarge, g5.24xlarge, g5.48xlarge, g5g.xlarge, g5g.2xlarge, g5g.4xlarge, g5g.8xlarge, g5g.16xlarge, g5g.metal, ml.p5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.p3dn.24xlarge , ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.16xlarge, ml.g4dn.12xlarge, ml.g5n.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge] +gpuInstances: [ p2.xlarge, p2.8xlarge, p2.16xlarge, p3.2xlarge, p3.8xlarge, p3.16xlarge, p3dn.24xlarge, p4d.24xlarge, p4de.24xlarge, p5.48xlarge, g3s.xlarge, g3.4xlarge, g3.8xlarge, g3.16xlarge, g4dn.xlarge, g4dn.2xlarge, g4dn.4xlarge, g4dn.8xlarge, g4dn.16xlarge, g4dn.12xlarge, g4dn.metal, g4ad.xlarge, g4ad.2xlarge, g4ad.4xlarge, g4ad.8xlarge, g4ad.16xlarge, g5.xlarge, g5.2xlarge, g5.4xlarge, g5.8xlarge, g5.16xlarge, g5.12xlarge, g5.24xlarge, g5.48xlarge, g5g.xlarge, g5g.2xlarge, g5g.4xlarge, g5g.8xlarge, g5g.16xlarge, g5g.metal, ml.p5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.p3dn.24xlarge , ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.g3s.xlarge, ml.g3.4xlarge, ml.g3.8xlarge, ml.g3.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.16xlarge, ml.g4dn.12xlarge, ml.g4dn.metal, ml.g4ad.xlarge, ml.g4ad.2xlarge, ml.g4ad.4xlarge, ml.g4ad.8xlarge, ml.g4ad.16xlarge, ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g5g.xlarge, g5g.2xlarge, ml.g5g.4xlarge, ml.g5g.8xlarge, ml.g5g.16xlarge, ml.g5g.metal] ## Tranium/Infrentia instance types neuronInstances: [ trn1.2xlarge, trn1.32xlarge, trn1n.32xlarge, inf1.xlarge, inf1.2xlarge, inf1.6xlarge, inf1.24xlarge, inf2.xlarge, inf2.8xlarge, inf2.24xlarge, inf2.48xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge, ml.inf1.xlarge, ml.inf1.2xlarge, ml.inf1.6xlarge, ml.inf1.24xlarge, ml.inf2.xlarge, ml.inf2.8xlarge, ml.inf2.24xlarge, ml.inf2.48xlarge] From 735a88f5f205a3b079d0573789720cda91bf61af Mon Sep 17 00:00:00 2001 From: Samarth Singh <45368705+sam6134@users.noreply.github.com> Date: Fri, 10 May 2024 16:10:02 +0100 Subject: [PATCH 4/4] Fix minor typos --- charts/amazon-cloudwatch-observability/values.yaml | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/charts/amazon-cloudwatch-observability/values.yaml b/charts/amazon-cloudwatch-observability/values.yaml index d8b64ac..7cda5ce 100644 --- a/charts/amazon-cloudwatch-observability/values.yaml +++ b/charts/amazon-cloudwatch-observability/values.yaml @@ -19,7 +19,7 @@ region: nodeLabelKey: node.kubernetes.io/instance-type ## NVIDIA GPU instance types -gpuInstances: [ p2.xlarge, p2.8xlarge, p2.16xlarge, p3.2xlarge, p3.8xlarge, p3.16xlarge, p3dn.24xlarge, p4d.24xlarge, p4de.24xlarge, p5.48xlarge, g3s.xlarge, g3.4xlarge, g3.8xlarge, g3.16xlarge, g4dn.xlarge, g4dn.2xlarge, g4dn.4xlarge, g4dn.8xlarge, g4dn.16xlarge, g4dn.12xlarge, g4dn.metal, g4ad.xlarge, g4ad.2xlarge, g4ad.4xlarge, g4ad.8xlarge, g4ad.16xlarge, g5.xlarge, g5.2xlarge, g5.4xlarge, g5.8xlarge, g5.16xlarge, g5.12xlarge, g5.24xlarge, g5.48xlarge, g5g.xlarge, g5g.2xlarge, g5g.4xlarge, g5g.8xlarge, g5g.16xlarge, g5g.metal, ml.p5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.p3dn.24xlarge , ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.g3s.xlarge, ml.g3.4xlarge, ml.g3.8xlarge, ml.g3.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.16xlarge, ml.g4dn.12xlarge, ml.g4dn.metal, ml.g4ad.xlarge, ml.g4ad.2xlarge, ml.g4ad.4xlarge, ml.g4ad.8xlarge, ml.g4ad.16xlarge, ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g5g.xlarge, g5g.2xlarge, ml.g5g.4xlarge, ml.g5g.8xlarge, ml.g5g.16xlarge, ml.g5g.metal] +gpuInstances: [ p2.xlarge, p2.8xlarge, p2.16xlarge, p3.2xlarge, p3.8xlarge, p3.16xlarge, p3dn.24xlarge, p4d.24xlarge, p4de.24xlarge, p5.48xlarge, g3s.xlarge, g3.4xlarge, g3.8xlarge, g3.16xlarge, g4dn.xlarge, g4dn.2xlarge, g4dn.4xlarge, g4dn.8xlarge, g4dn.16xlarge, g4dn.12xlarge, g4dn.metal, g4ad.xlarge, g4ad.2xlarge, g4ad.4xlarge, g4ad.8xlarge, g4ad.16xlarge, g5.xlarge, g5.2xlarge, g5.4xlarge, g5.8xlarge, g5.16xlarge, g5.12xlarge, g5.24xlarge, g5.48xlarge, g5g.xlarge, g5g.2xlarge, g5g.4xlarge, g5g.8xlarge, g5g.16xlarge, g5g.metal, ml.p5.48xlarge, ml.p4d.24xlarge, ml.p4de.24xlarge, ml.p3.2xlarge, ml.p3.8xlarge, ml.p3.16xlarge, ml.p3dn.24xlarge, ml.p2.xlarge, ml.p2.8xlarge, ml.p2.16xlarge, ml.g3s.xlarge, ml.g3.4xlarge, ml.g3.8xlarge, ml.g3.16xlarge, ml.g4dn.xlarge, ml.g4dn.2xlarge, ml.g4dn.4xlarge, ml.g4dn.8xlarge, ml.g4dn.16xlarge, ml.g4dn.12xlarge, ml.g4dn.metal, ml.g4ad.xlarge, ml.g4ad.2xlarge, ml.g4ad.4xlarge, ml.g4ad.8xlarge, ml.g4ad.16xlarge, ml.g5.xlarge, ml.g5.2xlarge, ml.g5.4xlarge, ml.g5.8xlarge, ml.g5.16xlarge, ml.g5.12xlarge, ml.g5.24xlarge, ml.g5.48xlarge, ml.g5g.xlarge, ml.g5g.2xlarge, ml.g5g.4xlarge, ml.g5g.8xlarge, ml.g5g.16xlarge, ml.g5g.metal] ## Tranium/Infrentia instance types neuronInstances: [ trn1.2xlarge, trn1.32xlarge, trn1n.32xlarge, inf1.xlarge, inf1.2xlarge, inf1.6xlarge, inf1.24xlarge, inf2.xlarge, inf2.8xlarge, inf2.24xlarge, inf2.48xlarge, ml.trn1.2xlarge, ml.trn1.32xlarge, ml.trn1n.32xlarge, ml.inf1.xlarge, ml.inf1.2xlarge, ml.inf1.6xlarge, ml.inf1.24xlarge, ml.inf2.xlarge, ml.inf2.8xlarge, ml.inf2.24xlarge, ml.inf2.48xlarge]