{"total":20,"rows":[{"id":"2604.13226","title":"KV Packet: Recomputation-Free Context-Independent KV Caching for LLMs","created":"2026-04-14","cited_by_count":10,"area":null},{"id":"2601.00397","title":"Revati: Transparent GPU-Free Time-Warp Emulation for LLM Serving","created":"2026-01-01","cited_by_count":5,"area":null},{"id":"2601.19139","title":"Native LLM and MLLM Inference at Scale on Apple Silicon","created":"2026-01-27","cited_by_count":5,"area":null},{"id":"2604.05438","title":"Residual-Mass Accounting for Partial-KV Decoding","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2609.39358","title":"Working Around the Compute Ceiling: Byte-Exact Memory in Galahad Makes LLM Reading a One-Time Cost LLM Reading a One-Time Cost","created":"2026-09-30","cited_by_count":1,"area":null},{"id":"2601.11822","title":"RAPID-Serve: Resource-efficient and Accelerated P/D Intra-GPU Disaggregation","created":"2026-01-16","cited_by_count":0,"area":null},{"id":"2603.02348","title":"Same Pieces, Different Servers: A Tetris Benchmark for AI Agents as Served","created":"2026-03-02","cited_by_count":0,"area":null},{"id":"2606.00050","title":"Grokers: Bottom-Up Inductive Comprehension and Write-Time Intelligence over Typed Knowledge Graphs","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2606.00946","title":"Lodestar: An Online-Learning LLM Inference Router","created":"2026-05-31","cited_by_count":0,"area":null},{"id":"2606.16352","title":"Communication-Efficient Verifiable Attention for LLM Inference","created":"2026-06-15","cited_by_count":0,"area":null},{"id":"2606.20295","title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2606.21238","title":"Recency/Frequency Adaptive KV Caching for Large Language Model Serving","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2607.17181","title":"Talaria: Session-Aware Serverless Serving of Hundred-Billion-Parameter LLMs","created":"2026-07-19","cited_by_count":0,"area":null},{"id":"2609.10790","title":"Composable CXL Memory as a Kubernetes-Native Shared Memory for LLM Serving","created":"2026-09-09","cited_by_count":0,"area":null},{"id":"2609.15021","title":"Shared KV Caching for Replicated 27B Inference: Correctness Failures and Performance Boundaries","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.15030","title":"Validating Hybrid-State Cache Recovery for GLM-5.3-Flash with vLLM and LMCache","created":"2026-09-14","cited_by_count":0,"area":null},{"id":"2609.26828","title":"Bridging LLM Serving and CXL-SSDs with Chunk-Aware KV Cache Management","created":"2026-09-20","cited_by_count":0,"area":null},{"id":"2609.35263","title":"WavePP: High-Throughput Pipeline Parallel LLM Prefill under Prefix Reuse","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.10845","title":"Real Long-Term Memory for AI: A 50-Million-Token Window That Is Faster and Cheaper Than Recompute","created":"2026-10-07","cited_by_count":0,"area":null},{"id":"2610.12133","title":"Rehearse Everything, Remember Nothing: Attic-KV Rehearses What Will Be Read","created":"2026-10-08","cited_by_count":0,"area":null}],"next_cursor":null}