17 docs tagged with "vllm"

Hands-on guide to deploying large open-source models on EKS, based on the GLM-5.1 experience

Building a domain-optimized model serving pipeline with LoRA Fine-tuning, Multi-LoRA Hot-swap, and SLM Cascade Routing

Comparing SageMaker HyperPod Inference Operator's managed KV cache, intelligent routing, and DPD with a Tiered Gateway, and clarifying its role and limitations as an L2 inference routing layer.

vLLM·llm-d·MoE·NeMo — AI framework layer for actual model serving, distributed inference, and fine-tuning on GPUs

EKS architecture overview for maximizing LLM Inference performance — starting point for vLLM, KV Cache-Aware Routing, Disaggregated Serving, LWS multi-node, and GPU autoscaling

A benchmark plan comparing Bedrock AgentCore as baseline against self-managed EKS (vLLM, llm-d, Bifrost/LiteLLM) across features, performance, and cost

Summary of core technologies like vLLM PagedAttention, Continuous Batching, FP8 KV Cache, and comparison of llm-d/NVIDIA Dynamo KV Cache-Aware Routing and Gateway configuration

Benchmark comparing performance and cost efficiency of GPU instances (p5, p4d, g6e) and AWS custom silicon (Trainium2, Inferentia2) for vLLM-based Llama 4 model serving

llm-d architecture concepts, KV Cache-aware routing, Disaggregated Serving, EKS Auto Mode integration strategy

The concept of LMCache — offloading KV cache beyond GPU memory to CPU and disk and sharing it across inference instances — and its relationship to vLLM prefix cache, NIXL, and kvaware routing.

End-to-end ML lifecycle management with Kubeflow + MLflow + vLLM + ArgoCD GitOps

A guide to the GPU infrastructure, inference framework, and inference optimization layers, with a single map of the end-to-end LLM inference request path and per-layer tuning levers — inference gateway, prefill/decode disaggregation, KV cache-aware routing, LMCache, and cache-hit strategy.

Architecture concepts, distributed deployment strategies, and performance optimization principles for Mixture of Experts models

Benchmark comparing Aggregated vs Disaggregated LLM serving performance using NVIDIA Dynamo — Running AIPerf 4 modes in an EKS environment

A customer-facing decision guide for evaluating and choosing self-hosted open-weight LLM deployment from the perspectives of token economics and data sovereignty.

vLLM PagedAttention, parallelization strategies, Multi-LoRA, and hardware support architecture

HuggingFace 리더보드 스캔부터 벤치마크 재현, 인스턴스별 성능 프로파일링, 멀티 타깃 배포 가이드 생성, 글로벌 스팟 캐파 확보까지 — 오픈 웨이트 모델 온보딩을 7단계 파이프라인으로 자동화하고 사람은 승인 게이트에만 개입하는 아키텍처를 제시합니다