# SIMPLE: Disaggregating Sampling from GPU Inference into a Decision Plane for Faster Distributed LLM Serving

arXiv: https://arxiv.org/abs/2512.00719 · HTML: https://mlsanity.com/paper/2512.00719/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Serving systems and request scheduling, one of 12 directions in Efficient LLM inference and serving.
- Builds on 24 of its 44 references that are in the map.
- First posted on arXiv 30 Nov 2025.

## Placed in

- Efficient LLM inference and serving / [Serving systems and request scheduling](https://mlsanity.com/inference/serving-systems-and-request-scheduling/)

## Builds on (most cited first, 24 of 24)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [Neural Machine Translation of Rare Words with Subword Units](https://mlsanity.com/paper/1508.07909/) (2015)
- [The Curious Case of Neural Text Degeneration](https://mlsanity.com/paper/1904.09751/) (2019)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processing](https://mlsanity.com/paper/1808.06226/) (2018)
- [Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism](https://mlsanity.com/paper/1909.08053/) (2019)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [SnapKV: LLM Knows What You are Looking for Before Generation](https://mlsanity.com/paper/2404.14469/) (2024)
- [H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models](https://mlsanity.com/paper/2306.14048/) (2023)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling](https://mlsanity.com/paper/2406.02069/) (2024)
- [QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving](https://mlsanity.com/paper/2405.04532/) (2024)
- [CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving](https://mlsanity.com/paper/2310.07240/) (2023)
- [Inference without Interference: Disaggregate LLM Inference for Mixed Downstream Workloads](https://mlsanity.com/paper/2401.11181/) (2024)
- [FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling](https://mlsanity.com/paper/2502.14856/) (2025)
- [VOCABTRIM: Vocabulary Pruning for Efficient Speculative Decoding in LLMs](https://mlsanity.com/paper/2506.22694/) (2025)
- [any4: Learned 4-bit Numeric Representation for LLMs](https://mlsanity.com/paper/2507.04610/) (2025)
- [DynaSpec: Context-aware Dynamic Speculative Sampling for Large-Vocabulary Language Models](https://mlsanity.com/paper/2510.13847/) (2025)

## Built on by (most cited first, 1 of 1)

- [FlashSampling: Fast and Memory-Efficient Exact Sampling](https://mlsanity.com/paper/2603.15854/) (2026)

## Abstract (arXiv)

As large language models (LLMs) scale out with tensor parallelism (TP) and pipeline parallelism (PP) and production stacks have aggressively optimized the data plane (attention/GEMM and KV cache), sampling, the decision plane that turns logits into tokens, becomes a new bottleneck. This creates a structural holdout: sampling neither expands with TP nor balances across PP stages, so its share of iteration time grows as GPUs get faster and it caps pipeline frequency at the last stage. We present SIMPLE, a stage-agnostic, sequence-parallel, overlappable decision plane that disaggregates sampling into a CPU-side service and shrinks its runtime footprint back to a minor, hidden role. SIMPLE combines: (1) sequence-parallel sampling, which shards work along the batch dimension and removes vocabulary-axis collectives; (2) a CPU-based algorithm with column-wise penalties and truncation-first filtering to realize single-pass, linear-time kernels; and (3) speculative hot-vocab sampling (SHVS), which samples on a small hot set with rejection-correctness and uses a simple sizing model to choose the hot-vocab size that maximizes throughput. In evaluation, SIMPLE improves end-to-end throughput by up to 96% and reduces P95 latency by 20-65%. Crucially, SIMPLE requires no user-side code changes and composes with existing data-plane optimizations, unlocking scaling benefits that compound with future GPU generations.