# Pre-Compiled Pipeline Shards for Distributed LLM Inference on Intel AI PC Fleets

arXiv: https://arxiv.org/abs/2608.19147 · HTML: https://mlsanity.com/paper/2608.19147/

## Key facts

- Cited by 3 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 13 of its 21 references that are in the map.
- First posted on arXiv 19 Aug 2026.

## 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, 13 of 13)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [Accelerating Large Language Model Decoding with Speculative Sampling](https://mlsanity.com/paper/2302.01318/) (2023)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Gemma 4 Technical Report](https://mlsanity.com/paper/2607.02770/) (2026)
- [GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM](https://mlsanity.com/paper/2403.05527/) (2024)
- [Petals: Collaborative Inference and Fine-tuning of Large Models](https://mlsanity.com/paper/2209.01188/) (2022)
- [Parallax: Efficient LLM Inference Service over Decentralized Environment](https://mlsanity.com/paper/2509.26182/) (2025)
- [Model-Distributed Inference for Large Language Models at the Edge](https://mlsanity.com/paper/2505.18164/) (2025)
- [TD-Pipe: Temporally-Disaggregated Pipeline Parallelism Architecture for High-Throughput LLM Inference](https://mlsanity.com/paper/2506.10470/) (2025)
- [SkipKV: Selective Skipping of KV Generation and Storage for Efficient Inference with Large Reasoning Models](https://mlsanity.com/paper/2512.07993/) (2025)

## Built on by (most cited first, 3 of 3)

- [CIDERS: Cloud-Edge LLM Collaborative Learning via Accelerating Personalized Bilevel Optimization](https://mlsanity.com/paper/2609.15664/) (2026)
- [Cascadia: A Control-Plane-Free Alternative to Hyperconverged AI Infrastructure](https://mlsanity.com/paper/2609.38697/) (2026)
- [Cascadia: Resident 975B MoE Inference on Eleven AI PCs](https://mlsanity.com/paper/2610.07219/) (2026)

## Abstract (arXiv)

Modern Intel AI PCs ship capable integrated GPUs and NPUs with 16+ GB of unified memory, and they spend considerable time idle. That is not enough memory to fit a large model such as a 70B-parameter LLM. We show that a handful of AIPCs, working together over an ordinary network, can serve models beyond the capability of any single one. We use pipeline parallelism: a model is split by layer into per-stage shards, each pre-compiled into an OpenVINO graph, so that every machine runs one shard and passes activations to the next. Three techniques make this fast enough to be useful. First, we recover the speed of the unsplit model: a naive per-stage export runs well below monolithic inference because it misses an OpenVINO GPU optimization, and injecting a beam_idx Gather into each shard triggers that optimization (the IndirectKVCache fusion) and brings the shards to parity. Second, we leverage speculative decoding on stateful OpenVINO models. Third, the pipeline serves several users at once by interleaving their requests across the stages, each request carrying its own cache (micro-batching). Together, a two-node Llama 3.1 8B INT4 pipeline serves two concurrent users at 1.79x the single-user throughput of the unsplit model on the same hardware, and the gap widens under simulated wide-area latency. The same design scales to a 70B model that no single fleet member can hold: a four-node deployment of Lunar Lake AI PCs on Intel Tiber Cloud serves a single user at interactive speed, with output token-for-token identical to the same four-node pipeline decoding without speculation. Code, raw benchmark logs, and reproduction scripts ship as a self-contained package at https://github.com/labscommunity/pipeline-sharded-inference-paper (in the top-level reproduction/ directory).