Mixture-of-Experts kernel engineering on Amazon SageMaker AI
2d
- Publicado
- Coletado
AWS engineers share kernel optimizations for fused Mixture-of-Experts (MoE) models on Amazon SageMaker AI: Swap-AB for WGMMA utilization, Triton backend routing for FP8 quantization, and eliminating Triton JIT recompilation. Together they deliver up to 10% higher throughput and up to 9% faster Time to First Token on H200 GPUs.
Mixture-of-Experts (MoE) is a sparsely-activated architecture that scales large language model (LLM) capacity while keeping per-token compute low. Because its operations account for a large share of total compute time, inefficiencies there directly raise request latency and cost. Therefore, optimizing MoE operations through kernel engineering offers the largest opportunity for performance gains. Fused MoE is a key optimization technique for the MoE architecture. A fused MoE system merges token…
O overfeed.news indexa e aponta. Publicamos um trecho curto — o artigo completo fica em AWS Machine Learning Blog.
Mais de AWS Machine Learning Blog
Entre para seguir esta fonte
Meta’s Muse Spark Open now available in Amazon SageMaker JumpStart
Muse Spark Open, Meta's coding-optimized open-weight model, is now available in Amazon SageMaker JumpStart. Deploy it to a SageMaker AI endpoint in your own AWS account using SageMaker Studio or the SageMaker Python SDK, and run your first inference request.
Trust in Depth: Giving agents more autonomy without losing control
Enterprise leaders want AI agents to take on more work but don't fully trust them to act correctly every time. Trust in Depth is AWS's layered approach-scope, know, bound, observe, and prove-that lets agents act on their own when their actions can be verified, reserving human judgment for the decisions that need it.
Build self-improving document processing using Amazon Bedrock AgentCore
Learn how to build an agentic intelligent document processing (IDP) system using Amazon Bedrock AgentCore that classifies, extracts, validates, and learns from business documents with minimal human intervention, automatically handling new document formats without manual template configuration.
Generate presentations with Amazon Bedrock AgentCore
This post walks you through building an AI agent system with Amazon Bedrock AgentCore that automates PowerPoint presentation creation from enterprise documents. A supervisor agent, Retrieval Augmented Generation, and Amazon Bedrock Guardrails generate grounded presentations in under 90 seconds.