cs.LGAug 9, 2025

PrismServe: Efficient LLM Serving on Heterogeneous Accelerator Clusters

Authors: Jinhao Zhang, Zicheng Yan, Boyang Zhang, Zeyu Liu, Daning Cheng, Yunquan Zhang, Guangming Tan, Xiang Gao

Organizations: Beijing University of Posts and Telecommunications, Beijing, China · University of Chinese Academy of Sciences, Beijing, China · Peng Cheng Laboratory, Shenzhen, China · North University of China, Taiyuan, China · 

Abstract

Serving large language models across heterogeneous accelerators is challenging because partitioning a replica across device types introduces communication overhead during autoregressive decoding, while deploying complete quantized replicas can degrade model quality. We present PrismServe, a serving system that combines request-level collaboration across heterogeneous hardware with a mixture of quantized experts derived from the same foundation model. Each expert executes within a group of same-type accelerators in a single node, while a two-level router selects an expert based on predicted response quality and then selects a replica according to load and prefix-cache locality. Implemented on unmodified vLLM, PrismServe achieves 2.0--2.6×\times the throughput of cross-node or cross-vendor full-precision pipelined deployments and reduces P99 time per output token by 55--65% when serving Qwen3-14B on 48 accelerators from three vendors. Across Qwen3-8B, Qwen3-14B, and Qwen3-32B on five downstream tasks, PrismServe outperforms the best single quantization method by 2.0--4.3 points while remaining within 1.4 points of full-precision accuracy. Our code is available at https://anonymous.4open.science/r/LLM-Inference-System-B000/

Figures & tables

Appendix figures & tables11 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

Apr 7, 2025

Prima.cpp: Fast 30-70B LLM Inference on Heterogeneous and Low-Resource Home Clusters

On-device inference offers privacy, offline use, and instant response, but consumer hardware restricts large language models (LLMs) to low throughput and capability. To overcome this challenge, we present prima.cpp, a distributed on-device inference system that runs 30-70B LLMs on consumer home clusters with mixed CPUs/GPUs, insufficient RAM/VRAM, slow disks, Wi-Fi links, and heterogeneous OSs. We introduce pipelined-ring parallelism (PRP) to overlap disk I/O with compute and communication, and address the prefetch-release conflict in mmap-based offloading. We further propose Halda, a heterogeneity-aware scheduler that co-optimizes per-device CPU/GPU workloads and device selection under RAM/VRAM constraints. On four consumer home devices, a 70B model reaches 674 ms/token TPOT with <6% memory pressure, and a 32B model with speculative decoding achieves 26 tokens/s. Compared with llama.cpp, exo, and dllama, our proposed prima.cpp achieves 5-17 times lower TPOT, supports fine-grained model sizes from 8B to 70B, ensures broader cross-OS and quantization compatibility, and remains OOM-free, while also being Wi-Fi tolerant, privacy-preserving, and hardware-independent. The code is available at https://github.com/OpenCPIL/prima.cpp.
May 15, 2026

A Few GPUs, A Whole Lotta Scale: Faithful LLM Training Emulation with PrismLLM

Large language model (LLM) training today runs on clusters spanning thousands of GPUs. While this scale enables rapid model advances, developing, debugging, and performance-tuning the training framework inevitably becomes complex and costly. This is because engineers often need to reproduce production behaviors to diagnose failures or evaluate optimizations, thereby demanding frequent and even exclusive access to production-scale clusters -- which becomes increasingly hard given that the majority of GPUs are already committed to production workloads. Simulation relies on complex performance models that are difficult to maintain, and downscaled experiments often fail to capture scale-dependent behaviors. We present PrismLLM to decouple large-scale execution from the need to access large clusters, enabling engineers to run and observe ranks of interest under faithful large-scale behavior using only a few GPUs. PrismLLM constructs a high-fidelity execution graph via a slicing-based approach that captures computation, communication, and dependencies of the target scale. Then, PrismLLM performs hybrid emulation where selected ranks execute the original program while the remaining ranks are replayed as virtual participants. Experiments on large-scale LLM training workloads show that PrismLLM accurately reproduces performance and memory behavior, achieving only 0.58% average error in iteration time and less than 0.01% error in peak GPU memory usage. PrismLLM can emulate clusters of up to 8192 GPUs using fewer than 1% of the physical GPUs required by the original deployment.
May 5, 2026

Coral: Cost-Efficient Multi-LLM Serving over Heterogeneous Cloud GPUs

The landscape of large language models (LLMs) has become increasingly fragmented, with no single model dominating the field. Meanwhile, cloud providers offer a diverse array of mid-tier and older-generation GPUs. These heterogeneous resources provide better availability and deliver comparable performance-per-dollar to top-tier hardware. To efficiently harness these GPUs for concurrent multi-LLM serving, we introduce Coral: an adaptive, heterogeneity-aware serving system. The key idea behind Coral is the joint optimization of resource allocation and replica serving strategies across all models. To keep pace with shifting throughput demands and resource availability, Coral employs a lossless, two-stage decomposition. This approach preserves joint optimality while reducing online solve times from hours to mere tens of seconds. Evaluations across 6 models and 20 GPU configurations demonstrate that Coral reduces serving costs by up to 2.79×\times compared to the strongest baseline, while delivering up to 2.39×\times higher goodput under scarce resource constraints.