diff --git a/recipes/overlays/gb200-eks-inference.yaml b/recipes/overlays/gb200-eks-inference.yaml index a6d9dac0d..4d2925aac 100644 --- a/recipes/overlays/gb200-eks-inference.yaml +++ b/recipes/overlays/gb200-eks-inference.yaml @@ -72,20 +72,3 @@ spec: intent: inference dependencyRefs: - nodewright-operator - - # NCCL fabric health checks. NET exercises EFA (inter-node), NVLS exercises - # MNNVL (intra-NVL72). Both matter for multi-node inference that spans the - # fabric (tensor-parallel serving, MoE expert parallelism); single-node - # deployments hit the WorkerCount < 2 skip path gracefully. Thresholds sized - # for a 2-node GB200 pair — will be raised once production NVL72 data is - # available. - validation: - performance: - checks: - - nccl-all-reduce-bw-net - - nccl-all-reduce-bw-nvls - constraints: - - name: nccl-all-reduce-bw-net - value: ">= 40" - - name: nccl-all-reduce-bw-nvls - value: ">= 500"