# Nitsum: Serving Tiered LLM Requests with Adaptive Tensor Parallelism

arXiv: https://arxiv.org/abs/2605.05467 · HTML: https://mlsanity.com/paper/2605.05467/

## 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 38 references that are in the map.
- First posted on arXiv 6 May 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)

- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [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)
- [DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model](https://mlsanity.com/paper/2405.04434/) (2024)
- [DistServe: Disaggregating Prefill and Decoding for Goodput-optimized Large Language Model Serving](https://mlsanity.com/paper/2401.09670/) (2024)
- [Splitwise: Efficient generative LLM inference using phase splitting](https://mlsanity.com/paper/2311.18677/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Llumnix: Dynamic Scheduling for Large Language Model Serving](https://mlsanity.com/paper/2406.03243/) (2024)
- [DynamoLLM: Designing LLM Inference Clusters for Performance and Energy Efficiency](https://mlsanity.com/paper/2408.00741/) (2024)
- [BurstGPT: A Real-world Workload Dataset to Optimize LLM Serving Systems](https://mlsanity.com/paper/2401.17644/) (2024)
- [ServeGen: Workload Characterization and Generation of Large Language Model Serving in Production](https://mlsanity.com/paper/2505.09999/) (2025)
- [Hierarchical Autoscaling for Large Language Model Serving with Chiron](https://mlsanity.com/paper/2501.08090/) (2025)
- [SCOOT: SLO-Oriented Performance Tuning for LLM Inference Engines](https://mlsanity.com/paper/2408.04323/) (2024)

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

- [Cascade: Exploiting SLO-Aware latency budget for fair and high goodput LLM inference serving](https://mlsanity.com/paper/2608.06557/) (2026)
- [FleetSieve: Decision-Critical Profiling for SLO-Aware LLM Fleet Configuration](https://mlsanity.com/paper/2608.19659/) (2026)
- [Scaling LLM Inference via Parallelism: Throughput-Latency Trade-off](https://mlsanity.com/paper/2610.19405/) (2026)

## Abstract (arXiv)

LLM serving is increasingly multi-tenant: the same deployment must handle latency-critical interactive requests and more relaxed background workloads under a fixed GPU budget. This creates a tiered-SLO setting where maximizing overall goodput (requests that satisfy both TTFT and TPOT targets) is challenging because workload mix, request lengths, and load intensity vary over time. Existing systems mainly optimize request-level controls (e.g., queuing and batching) while keeping execution configuration largely static, which limits adaptation under multi-tier contention. We present Nitsum, a distributed LLM serving system that treats tensor parallelism (TP) as a first-class runtime control surface rather than a static deployment choice. Nitsum jointly optimizes TP level, prefill/decode GPU split, and request scheduling. To make frequent TP adaptation practical, Nitsum introduces TP-aware weight reuse and fast KV migration. Experiments on real traces and targeted microbenchmarks show that Nitsum improves SLO-compliant goodput over SoTA by up to 5.3 times.