13 docs tagged with "benchmark"

An unexecuted plan to compare runtime hosting, model serving and gateways under controlled quality, isolation, performance and cost requirements

Collection of EKS environment performance benchmark reports — Networking, AI/ML Inference, Infrastructure & Operations, AI Agents

Measured report that ran a RealWorld backend implementation task in a Ralph loop five times on each of 14 models in Amazon Bedrock us-east-1 and compares completion, tokens, cost and LLM requests

Architecture comparison, versioned conformance evidence, reproducible feature and performance test plans, and local validation for Gateway API implementations

Hybrid cloud infrastructure network and storage performance benchmark

EKS cluster infrastructure performance benchmark - Network, DNS, Autoscaling

Official GPU, Trainium2 and Inferentia2 specifications, Llama 4 model requirements, and a plan for measuring performance and cost

Hardware requirements, four workload families, and a measurement plan for comparing aggregated and disaggregated NVIDIA Dynamo serving on EKS

Planned common-model EKS baseline with explicit cache settings, reproducibility and complete cost gates

Planned cold/warm exact-prefix experiments and a separate semantic-cache correctness track using the EKS baseline

Evidence boundaries and the registered plan for a common-model coding-agent comparison across Bedrock and self-hosted EKS

Security policy enforcement and operations tool performance benchmark

A benchmark report comparing network and application performance of VPC CNI and Cilium CNI across 5 scenarios (kube-proxy, kube-proxy-less, ENI, tuning) in an EKS environment