# Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC

arXiv: https://arxiv.org/abs/2604.07609 · HTML: https://mlsanity.com/paper/2604.07609/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 52 references that are in the map.
- First posted on arXiv 8 Apr 2026.

## Builds on (most cited first, 18 of 18)

- [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)
- [FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness](https://mlsanity.com/paper/2205.14135/) (2022)
- [FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning](https://mlsanity.com/paper/2307.08691/) (2023)
- [Fast Inference from Transformers via Speculative Decoding](https://mlsanity.com/paper/2211.17192/) (2022)
- [GQA: Training Generalized Multi-Query Transformer Models from Multi-Head Checkpoints](https://mlsanity.com/paper/2305.13245/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [Fast Transformer Decoding: One Write-Head is All You Need](https://mlsanity.com/paper/1911.02150/) (2019)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [FlexGen: High-Throughput Generative Inference of Large Language Models with a Single GPU](https://mlsanity.com/paper/2303.06865/) (2023)
- [DeepSpeed Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale](https://mlsanity.com/paper/2207.00032/) (2022)
- [Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference](https://mlsanity.com/paper/2308.12066/) (2023)
- [vAttention: Dynamic Memory Management for Serving LLMs without PagedAttention](https://mlsanity.com/paper/2405.04437/) (2024)
- [AQUA: Network-Accelerated Memory Offloading for LLMs in Scale-Up GPU Domains](https://mlsanity.com/paper/2407.21255/) (2024)
- [HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location](https://mlsanity.com/paper/2501.14808/) (2025)
- [Niyama : Breaking the Silos of LLM Inference Serving](https://mlsanity.com/paper/2503.22562/) (2025)
- [ConServe: Fine-Grained GPU Harvesting for LLM Online and Offline Co-Serving](https://mlsanity.com/paper/2410.01228/) (2024)
- [Lovelock: Towards Smart NIC-hosted Clusters](https://mlsanity.com/paper/2309.12665/) (2023)

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

- [Taking Tokenization off the Host for Agentic LLM Serving](https://mlsanity.com/paper/2610.13325/) (2026)

## Abstract (arXiv)

Large Language Model (LLM) inference is rapidly becoming a core datacenter service, yet current serving stacks keep the host CPU on the critical path for orchestration and token-level control. This makes LLM performance sensitive to CPU interference, undermining application colocation and forcing operators to reserve CPU headroom, leaving substantial capacity unutilized. We introduce Blink, an end-to-end serving architecture that removes the host CPU from the steady-state inference path by redistributing responsibilities across a SmartNIC and a GPU. Blink offloads request handling to the SmartNIC, which delivers inputs directly into GPU memory via RDMA, and replaces host-driven scheduling with a persistent GPU kernel that performs batching, scheduling, and KV-cache management without CPU involvement. Evaluated against TensorRT-LLM, vLLM, and SGLang, Blink outperforms all baselines even in isolation, reducing pre-saturation P99 TTFT by up to 8.47× and P99 TPOT by up to 3.40×, improving decode throughput by up to 2.1×, and reducing energy per token by up to 48.6%. Under CPU interference, Blink maintains stable performance, while existing systems degrade by up to two orders of magnitude.