---
type: "raw_signal"
id: "scaling-moe-reinforcement-learning-on-amazon-eks-with-4c8ea3"
slug: "scaling-moe-reinforcement-learning-on-amazon-eks-with-4c8ea3"
title: "Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughput"
description: "AWS published an Amazon EKS architecture for scaling mixture-of-experts reinforcement learning with Elastic Fabric Adapter, DeepEP, and Amazon S3."
retrieval_nugget: "AWS published an Amazon EKS architecture for scaling mixture-of-experts reinforcement learning with Elastic Fabric Adapter, DeepEP, and Amazon S3."
observed_at: "2026-09-26"
record_date: "2026-09-26"
date_kind: "observed_at"
why_it_matters: "AWS published an Amazon EKS architecture for scaling mixture-of-experts reinforcement learning with Elastic Fabric Adapter, DeepEP, and Amazon S3. The company reports a 40% increase in aggregate reinforcement-learning rollout throughput for large-scale RLHF and GRPO training. The result is a vendor-reported implementation outcome, not a general benchmark across MoE workloads."
novelty: "notable"
verification_level: "source-linked"
signal_type: "update"
source_platform: "aws.amazon.com"
topics: []
entities: []
related_patterns: []
source_url: "https://aws.amazon.com/blogs/machine-learning/scaling-moe-reinforcement-learning-on-amazon-eks-with-efa-and-deepep-with-40-more-throughput"
source_urls: ["https://aws.amazon.com/blogs/machine-learning/scaling-moe-reinforcement-learning-on-amazon-eks-with-efa-and-deepep-with-40-more-throughput"]
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "signal:scaling-moe-reinforcement-learning-on-amazon-eks-with-4c8ea3"
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/signals/scaling-moe-reinforcement-learning-on-amazon-eks-with-4c8ea3/","markdown":"https://newruntime.com/signals/scaling-moe-reinforcement-learning-on-amazon-eks-with-4c8ea3.md","json":"https://newruntime.com/signals/scaling-moe-reinforcement-learning-on-amazon-eks-with-4c8ea3.json"}
---

# Scaling MoE reinforcement learning on Amazon EKS with EFA and DeepEP with 40% more throughput

## Retrieval answer

AWS published an Amazon EKS architecture for scaling mixture-of-experts reinforcement learning with Elastic Fabric Adapter, DeepEP, and Amazon S3.

AWS published an Amazon EKS architecture for scaling mixture-of-experts reinforcement learning with Elastic Fabric Adapter, DeepEP, and Amazon S3. The company reports a 40% increase in aggregate reinforcement-learning rollout throughput for large-scale RLHF and GRPO training. The result is a vendor-reported implementation outcome, not a general benchmark across MoE workloads.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- collection: [Raw Signals](https://newruntime.com/signals.json): Open every source-linked raw signal.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)