Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs

arXiv:2610.19801 · cs.CL, cs.DC, cs.PF · Submitted 2026-10-14 · Read on arXiv

cs.CL, cs.DC, cs.PF

Submitted: 2026-10-14

Updated: 2026-10-14

Comments: 42 pages (16-page main text, references, and supplementary material), 14 figures, 35 tables. The incremental tokenization path and the fast encoder are open source in toktier at https://github.com/asu-idi/toktier. The chunk-parallel path, the CPU pool scheduler, and the SGLang adapter will be released in the same repository

Code: https://github.com/asu-idi/toktier

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Tokenization — 1× in this paper · explained in 2 episodes

Sources

• Formalizing BPE Tokenization
• Characterizing CPU-Induced Slowdowns in Multi-GPU LLM Inference
• DeepSeek-V3 Technical Report
• SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?
• Incremental BPE Tokenization
• GPUTOK: GPU Accelerated Byte Level BPE Tokenization
• The Llama 3 Herd of Models
• gpt-oss-120b & gpt-oss-20b Model Card
• Qwen3 Technical Report
• Taking Tokenization off the Host for Agentic LLM Serving
• CacheWise: Understanding Workloads and Optimizing KVCache Management for Efficiently Serving LLM Coding Agents
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• SWE-smith: Scaling Data for Software Engineering Agents
• ReAct: Synergizing Reasoning and Acting in Language Models
• BlockBPE: Parallel BPE Tokenization
• TokTier: Exact Stateful CPU+GPU Tokenization for Agentic LLM Serving
• TraceLab: Characterizing Coding Agent Workloads for LLM Serving

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering