Disaggregation of Prefilling and Decoding using Pipelined Engines
This strategy, known as the disaggregation of prefilling and decoding, implements continuous batching by using two specialized hardware engines. A dedicated 'Engine 1' performs prefilling for a batch of requests. Once complete, the generated Key-Value (KV) cache is sent to a separate 'Engine 2' for decoding. The primary benefit of this pipeline is that Engine 1 can immediately start prefilling the next batch while Engine 2 is decoding the first. This overlapping of computations is key to improving computational efficiency and maximizing hardware utilization.
0
1
Tags
Ch.5 Inference - Foundations of Large Language Models
Foundations of Large Language Models
Foundations of Large Language Models Course
Computing Sciences
Related
Iteration in Continuous Batching
General Process of Continuous Batching
Example of Interleaving Prefilling and Decoding in Continuous Batching
Overhead of Dynamic Batch Reorganization in Continuous Batching
Memory Fragmentation in LLM Inference
Prefilling-Prioritized Strategy in Continuous Batching
Simple Iteration-level Scheduling
Priority-Based Scheduling in LLM Inference
Custom Priority Policies in LLM Scheduling
Disaggregation of Prefilling and Decoding using Pipelined Engines
Comparison of Continuous (Prefilling-Prioritized) vs. Standard (Decoding-Prioritized) Batching
LLM Inference Scheduling Strategy
An LLM inference server is processing a batch of three long-running requests. In the middle of this process, after several computational steps have already been completed for the initial batch, a new, short request arrives. How would a system implementing continuous batching most likely handle this new request in the next computational step?
An LLM inference system is designed to maximize hardware utilization. Which of the following operational descriptions best illustrates the core principle of continuous batching, distinguishing it from a static batching approach?
Formula for KV Cache Prefilling
Prefix Caching for LLM Inference
Prefilling as an Encoding Process
Disaggregation of Prefilling and Decoding using Pipelined Engines
Prefilling in One Go (Standard Prefilling)
A large language model is given a 1000-token document to process before it begins generating a new, multi-token response. Which statement best analyzes the fundamental computational difference between how the model processes the initial 1000-token document versus how it will subsequently generate each new token for its response?
LLM Inference Performance Analysis
Parallel Self-Attention in the Prefilling Phase
The Role and Output of the Prefilling Phase
You run an internal LLM inference service for empl...
You’re on-call for an internal LLM chat service. M...
You operate a GPU-backed LLM service that uses con...
Your company’s internal LLM service handles many c...
Evaluating a serving design that combines prefix caching with paged KV memory under mixed prompt lengths
Choosing a KV-cache strategy for shared-prefix traffic under GPU memory pressure
Diagnosing and Redesigning KV-Cache Memory Behavior in a Multi-Tenant LLM Serving Stack
Stabilizing latency and GPU memory in a chat-completions service with shared system prompts
Root-cause and mitigation plan for OOMs and latency spikes during shared-prefix, long-generation traffic
Post-incident analysis: KV-cache growth, fragmentation, and shared-prefix reuse in a streaming LLM service
Decoding Network for KV Cache Generation
Diagram of the Decoding Phase
Single-Step Generation with a KV Cache
Comparison of Prefilling and Decoding Phases
Disaggregation of Prefilling and Decoding using Pipelined Engines
After a large language model processes an initial prompt, it enters a generation stage where it produces the output sequence one token at a time. In each step of this stage, a new query vector is generated for the current position, and it must perform an attention operation over the key-value pairs of the initial prompt plus all the key-value pairs of the tokens generated in previous steps. As the output sequence gets longer, what becomes the most significant performance bottleneck for generating each new token?
A large language model has finished processing an initial prompt and is about to generate the first token of its response. Arrange the following events in the correct chronological order for this single generation step.
Evaluating an Inference Optimization Proposal
You run an internal LLM inference service for empl...
You’re on-call for an internal LLM chat service. M...
You operate a GPU-backed LLM service that uses con...
Your company’s internal LLM service handles many c...
Evaluating a serving design that combines prefix caching with paged KV memory under mixed prompt lengths
Choosing a KV-cache strategy for shared-prefix traffic under GPU memory pressure
Diagnosing and Redesigning KV-Cache Memory Behavior in a Multi-Tenant LLM Serving Stack
Stabilizing latency and GPU memory in a chat-completions service with shared system prompts
Root-cause and mitigation plan for OOMs and latency spikes during shared-prefix, long-generation traffic
Post-incident analysis: KV-cache growth, fragmentation, and shared-prefix reuse in a streaming LLM service
Decoding Phase Goal Formula
Learn After
An LLM inference system is designed with two specialized hardware engines operating in a pipeline. Engine A processes the initial prompts for a batch of user requests to generate their internal state. This state is then passed to Engine B, which handles the step-by-step generation of the response tokens for that same batch. As soon as Engine A finishes with the first batch, it immediately begins processing the initial prompts for a second, new batch of requests while Engine B is still generating tokens for the first batch. What is the primary computational advantage of this two-engine architecture?
Optimizing LLM Inference Throughput
Example of Pipelined Prefilling and Decoding with Two Engines
Pipelined Engine Efficiency