HETEROVLM: Edge Multi-Request Vision-Language Model Serving on a Heterogeneous Versal SoC with AI Engines and Programmable Logic

Edge devices in vehicles and robots serve concurrent requests with different deadlines to a vision-language model (VLM), each mixing a compute-bound encoder and prefill with a memory-bound decode. GPU serving targets datacenter throughput with per-iteration host scheduling: an urgent request waits for the running iteration, and small-batch decode costs much energy per token. Prior accelerators on Versal AI Engine (AIE) SoCs map one model onto a fixed AIE dataflow graph for one input stream, without decode or request scheduling. HETEROVLM keeps the AIE graph static and makes it schedulable. The AIE array runs the encoder, prefill and attention, and the programmable logic (PL) holds GEMV engines for small decode steps and a scheduler that orders short work units by class and deadline. Concurrent requests share one decode step that reads the weights once. An urgent request preempts at a work-unit boundary, and the paused request resumes from its results in DDR. On an AMD Versal VC1902, text and camera questions get their first tokens in 140 and 303 ms. HETEROVLM decodes a single request 1.3x and 4.0x faster than NVIDIA Tesla T4 and Jetson Orin Nano GPUs, with 61% and 73% of their energy per token, and uses 51% of the energy per token of an NVIDIA GeForce RTX 3090 Ti. The same bitstream serves multiple VLMs by loading their own instruction programs and weights. A demo is available at https://anonymous.4open.science/r/demo heterovlm-EFM2/.

Authors

Publication Details

Journal
arXiv (Cornell University)
Published
2026-11-18
DOI
https://doi.org/10.48550/arxiv.2611.23878
Primary Topic
Embedded Systems Design Techniques
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

HETEROVLM: Edge Multi-Request Vision-Language Model Serving on a Heterogeneous Versal SoC with AI Engines and Programmable Logic

Saptarshi Mitra, Ye Qiao, Yu-an Chou, Zhiheng Chen et al.
arXiv (Cornell University)
Embedded Systems Design Techniques
preprint

HETEROVLM: Edge Multi-Request Vision-Language Model Serving on a Heterogeneous Versal SoC with AI Engines and Programmable Logic

Saptarshi Mitra, Ye Qiao, Yu-an Chou, Zhiheng Chen, Yifan Zhang, Sitao Huang
preprint en

Abstract

Edge devices in vehicles and robots serve concurrent requests with different deadlines to a vision-language model (VLM), each mixing a compute-bound encoder and prefill with a memory-bound decode. GPU serving targets datacenter throughput with per-iteration host scheduling: an urgent request waits for the running iteration, and small-batch decode costs much energy per token. Prior accelerators on Versal AI Engine (AIE) SoCs map one model onto a fixed AIE dataflow graph for one input stream, without decode or request scheduling. HETEROVLM keeps the AIE graph static and makes it schedulable. The AIE array runs the encoder, prefill and attention, and the programmable logic (PL) holds GEMV engines for small decode steps and a scheduler that orders short work units by class and deadline. Concurrent requests share one decode step that reads the weights once. An urgent request preempts at a work-unit boundary, and the paused request resumes from its results in DDR. On an AMD Versal VC1902, text and camera questions get their first tokens in 140 and 303 ms. HETEROVLM decodes a single request 1.3x and 4.0x faster than NVIDIA Tesla T4 and Jetson Orin Nano GPUs, with 61% and 73% of their energy per token, and uses 51% of the energy per token of an NVIDIA GeForce RTX 3090 Ti. The same bitstream serves multiple VLMs by loading their own instruction programs and weights. A demo is available at https://anonymous.4open.science/r/demo heterovlm-EFM2/.

arXiv (Cornell University)
Embedded Systems Design Techniques
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon