3 papers
cs.CL2026
Delta Tokenizer: Reference-Identical Tokenization of Session Deltas and Segment-Parallelism for Long Prompts on Multicore CPUs
Zhenyu Zhang, Zhichao Cao
An agent that drives an LLM sends the model the same conversation again and again, and each turn adds only a little text at the end. Inference engines reuse the KV cache of the sha…
cs.CL2026
TokTier: Exact Stateful CPU+GPU Tokenization for Agentic LLM Serving
Zhenyu Zhang, Zhichao Cao
LLM serving caches prompt KV state, yet most front ends still re-tokenize the full request on every call. Coding agents pay most: sessions repeatedly submit a long transcript after…
cs.DB2025
StorageXTuner: An LLM Agent-Driven Automatic Tuning Framework for Heterogeneous Storage Systems
Qi Lin, Zhenyu Zhang, Viraj Thakkar +3
Automatically configuring storage systems is hard: parameter spaces are large and conditions vary across workloads, deployments, and versions. Heuristic and ML tuners are often sys…