DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
Split a request's timeline into prefill and decode GPU pools — 4.48x more requests under SLO.
Zhong et al. · OSDI 2024 · Serving. Read the paper ↗
A free, interactive, animated visual explainer of DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving — every exhibit computed from the real formulas, with verbatim quotes from the source.
Questions
- What is DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving?
- Split a request's timeline into prefill and decode GPU pools — 4.48x more requests under SLO.
- Who published DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving, and where?
- Zhong et al. — OSDI 2024 (arXiv:2401.09670).
- Where can I find a visual explainer of DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving?
- Right here — a free, interactive, animated walkthrough of the whole paper, with exhibits computed from the real formulas and verbatim quotes from the source.
Related explainers
- PagedAttention (vLLM)
- Efficiently Scaling Transformer Inference
- Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
- Fast Inference from Transformers via Speculative Decoding
- EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
- Efficient Streaming Language Models with Attention Sinks