Official Technical Resources: NVIDIA (page 3)
Official Technical Resources · NVIDIA: 264 entries in total; this page lists entries 31–45.
Disaggregated Serving
The prefill and decode phases of LLM requests have different computation characteristics and memory footprints.
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
Distributed Runtime
Dynamo's DistributedRuntime is the core infrastructure in the framework that enables distributed communication and coordination between different Dynamo…
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
Sidecar Backends
Run Dynamo beside a stock inference engine through its native gRPC API.
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
SGLang for Agentic Workloads
Priority scheduling and session control for multi-turn agentic serving
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: AI Agent · Tool Calling · LLM Inference Optimization
Link last checked: 2026-09-25
Using HiCache
Hierarchical KV caching with tier-aware router integration
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
KV Cache Offloading
CPU and disk offloading integrations for vLLM in Dynamo
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
vLLM-Omni Disaggregated Multi-Stage Serving
Architecture of multi-stage vLLM-Omni pipelines (e.g. AR + Diffusion), with each stage on its own GPU for independent scaling and isolation.
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
KVBM Design
This document provides an in-depth look at the architecture, components, framework integrations via the connector API, and the detailed workings of the Dynamo…
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
Planner Design
The Planner is Dynamo's autoscaling controller.
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
Deficit Round Robin Queue Scheduling
Weighted arbitration across router policy classes
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
Disaggregated Serving
Prefill and decode routing with the Dynamo router
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
Router Design
This document describes the internal architecture of the Dynamo KV Router, including block tracking mechanisms, the KV cache optimization system, event…
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
Router Filtering
Candidate eligibility, DP-rank filtering, and queue backpressure boundaries
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
Routing Concepts
Cost model, worker selection, and routing primitives for the Dynamo router
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25
Embedding Cache
Cache vision encoder embeddings to skip re-encoding repeated multimodal content
Evidence use: For understanding GPU computing, training, retrieval, inference serving, reliability or deployment decisions.
Limitations: Directly evidences only the implementation and claims of NVIDIA's technology stack. Recheck versioned interfaces and experimental capabilities before use.
Related concepts: Model Deployment Options · LLM Inference Optimization · LLM Observability and Tracing
Link last checked: 2026-09-25