{"total":29,"rows":[{"id":"2405.14366","title":"MiniCache: KV Cache Compression in Depth Dimension for Large Language Models","created":"2024-05-23","cited_by_count":125,"area":"inference"},{"id":"2312.04916","title":"EE-LLM: Large-Scale Training and Inference of Early-Exit Large Language Models with 3D Parallelism","created":"2023-12-08","cited_by_count":69,"area":"inference"},{"id":"2502.04420","title":"KVTuner: Sensitivity-Aware Layer-Wise Mixed-Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference","created":"2025-02-06","cited_by_count":40,"area":"inference"},{"id":"2406.13035","title":"D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models","created":"2024-06-18","cited_by_count":31,"area":"inference"},{"id":"2405.19325","title":"Nearest Neighbor Speculative Decoding for LLM Generation and Attribution","created":"2024-05-29","cited_by_count":25,"area":"inference"},{"id":"2410.03960","title":"SwiftKV: Fast Prefill-Optimized Inference with Knowledge-Preserving Model Transformation","created":"2024-10-04","cited_by_count":19,"area":"inference"},{"id":"2505.17272","title":"Zebra-Llama: Towards Extremely Efficient Hybrid Models","created":"2025-05-22","cited_by_count":18,"area":"inference"},{"id":"2504.10724","title":"HELIOS: Adaptive Model And Early-Exit Selection for Efficient LLM Inference Serving","created":"2025-04-14","cited_by_count":8,"area":"inference"},{"id":"2410.15704","title":"Residual vector quantization for KV cache compression in large language model","created":"2024-10-21","cited_by_count":7,"area":"inference"},{"id":"2506.08018","title":"KVmix: Gradient-Based Layer Importance-Aware Mixed-Precision Quantization for KV Cache","created":"2025-05-18","cited_by_count":5,"area":"inference"},{"id":"2510.11236","title":"XQuant: Achieving Ultra-Low Bit KV Cache Quantization with Cross-Layer Compression","created":"2025-10-13","cited_by_count":5,"area":"inference"},{"id":"2510.16040","title":"Kelle: Co-design KV Caching and eDRAM for Efficient LLM Serving in Edge Computing","created":"2025-10-16","cited_by_count":5,"area":"inference"},{"id":"2409.16546","title":"AlignedKV: Reducing Memory Access of KV-Cache with Precision-Aligned Quantization","created":"2024-09-25","cited_by_count":4,"area":"inference"},{"id":"2502.13502","title":"PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference","created":"2025-02-19","cited_by_count":3,"area":"inference"},{"id":"2506.17286","title":"GTA: Grouped-head latenT Attention","created":"2025-06-15","cited_by_count":3,"area":"inference"},{"id":"2509.16598","title":"PruneCD: Contrasting Pruned Self Model to Improve Decoding Factuality","created":"2025-09-20","cited_by_count":3,"area":"inference"},{"id":"2505.17787","title":"Titanus: Enabling KV Cache Pruning and Quantization On-the-Fly for LLM Acceleration","created":"2025-05-23","cited_by_count":2,"area":"inference"},{"id":"2502.16886","title":"ReFreeKV: Towards Threshold-Free KV Cache Compression","created":"2025-02-24","cited_by_count":1,"area":"inference"},{"id":"2504.08838","title":"SD$^2$: Self-Distilled Sparse Drafters","created":"2025-04-10","cited_by_count":1,"area":"inference"},{"id":"2511.18936","title":"SWAN: Sparse Winnowed Attention for Reduced Inference Memory via Decompression-Free KV-Cache Compression","created":"2025-11-24","cited_by_count":1,"area":"inference"},{"id":"2511.02681","title":"Optimal Singular Damage: Efficient LLM Inference in Low Storage Regimes","created":"2025-11-04","cited_by_count":0,"area":"inference"},{"id":"2511.21408","title":"Subjective Depth and Timescale Transformers: Learning Where and When to Compute","created":"2025-11-26","cited_by_count":0,"area":"inference"},{"id":"2605.23057","title":"RequestRouter: Request-Boundary Routing for Efficient Single-GPU LLM Inference","created":"2026-05-21","cited_by_count":0,"area":"inference"},{"id":"2605.27646","title":"Hurwitz Quaternion Multiplicative Quantization for KV Cache Compression","created":"2026-05-26","cited_by_count":0,"area":"inference"},{"id":"2605.27763","title":"A Paired Testing Protocol for Batch-Conditioned Refusal Robustness in LLM Serving","created":"2026-05-26","cited_by_count":0,"area":"inference"},{"id":"2606.25097","title":"Speculative Decoding at Temperature Zero: A Scoped Safety-Invariance Screen with a 48,072-Sample Expansion","created":"2026-06-23","cited_by_count":0,"area":"inference"},{"id":"2607.01065","title":"GSRQ: Gain-Shape Residual Quantization for Sub-1-bit KV Cache","created":"2026-07-01","cited_by_count":0,"area":"inference"},{"id":"2607.08930","title":"BlockServe: Block-Grained Continuous Batching for High-Throughput Diffusion LLM Serving","created":"2026-07-09","cited_by_count":0,"area":"inference"},{"id":"2609.11799","title":"SpecGuard: Inference-Time Backdoor Detection For Free","created":"2026-09-10","cited_by_count":0,"area":"inference"}],"next_cursor":null}