Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving
Schedule the KV cache, not the GPU: disaggregated prefill/decode serving that survives overload.
Qin et al. · arXiv 2024 · Serving. Read the paper ↗
A free, interactive, animated visual explainer of Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving — every exhibit computed from the real formulas, with verbatim quotes from the source.
Questions
- What is Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving?
- Schedule the KV cache, not the GPU: disaggregated prefill/decode serving that survives overload.
- Who published Mooncake: A KVCache-centric Disaggregated Architecture for LLM Serving, and where?
- Qin et al. — arXiv 2024 (arXiv:2407.00079).
- Where can I find a visual explainer of Mooncake: A KVCache-centric Disaggregated Architecture for LLM 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
- Fast Inference from Transformers via Speculative Decoding
- EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty
- AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration
- DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving
- CacheBlend: Fast Large Language Model Serving for RAG with Cached Knowledge Fusion
- Efficient Streaming Language Models with Attention Sinks