ReLLM-OS: Chip Virtualization of Hardware Large Language Models (LLMs) over a Reusable Transformer Datapath
Journal of Superintelligence · 02.11.2026 · 1 (2) · 9
DOI: 10.3390/superintelligence1020009 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Superintelligence, online erschienen am 02.11.2026. Verfasst von Anastasios N. Bikos. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Large language model (LLM) accelerators are commonly optimized for fixed model structures and isolated inference workloads, whereas emerging artificial-intelligence operating systems (AI OSs) primarily virtualize agents, memory, and tools in software. Reusable hardware, phase-aware serving, operating-system-level composition, and automata-based formalisms each exist separately in prior work; this architecture paper treats them simultaneously to ask whether LLM inference can be exposed as a secure, reusable hardware service. We introduce HCDP-LLM, an AI-OS-managed hierarchical common datapath that composes reusable tensor, reduction, nonlinear, quantization, memory, and key–value (KV)-cache modules through model capsules and a Moore finite-state controller. The architecture is formalized as a finite-precision multi-tape computational transducer, enabling deterministic checkpointing, migration, isolation, and Turing-machine-based bit-time, space, and I/O analysis. An explicit derivation on this transducer yields quadratic prompt-attention work, context-linear per-token attention and KV-cache storage, and separates compute-dominated prefill from bandwidth-dominated decoding. The formal model separates finite-state physical realizations from a scalable family with extensible memory that can support universal computation; a worked example derives from it the admission limit, lane allocation, and rebinding granularity of a 7B-parameter model on one reconfigurable accelerator. No prototype measurements or simulations are reported; a pre-specified evaluation protocol with a control-plane-disabled baseline, which isolates the abstraction-layer cost, defines how a field-programmable gate array (FPGA) or system-on-chip prototype must test the resulting position: Hardware LLMs as runtime-composable, weight-programmable inference fabrics rather than permanently hardwired models.
Zitieren
APA
Bikos, A. N. (2026). ReLLM-OS: Chip Virtualization of Hardware Large Language Models (LLMs) over a Reusable Transformer Datapath. Journal of Superintelligence, 1(2), 9. https://doi.org/10.3390/superintelligence1020009
Vancouver
Bikos AN. ReLLM-OS: Chip Virtualization of Hardware Large Language Models (LLMs) over a Reusable Transformer Datapath. Journal of Superintelligence. 2026;1(2):9. doi:10.3390/superintelligence1020009
BibTeX
@article{Bikos2026,
author = {Bikos, Anastasios N.},
title = {ReLLM-OS: Chip Virtualization of Hardware Large Language Models (LLMs) over a Reusable Transformer Datapath},
journal = {Journal of Superintelligence},
year = {2026},
volume = {1},
number = {2},
pages = {9},
doi = {10.3390/superintelligence1020009}
}
EUVIMED