InfiniLoRA: Disaggregated Multi-LoRA Serving for Large Language Models
cs.DC
Submitted: 2026-04-08
Updated: 2026-11-03
Terminology
Sources
- MapReduce LoRA: Advancing the Pareto Front in Multi-Preference Optimization for Generative Models
- Punica: Multi-Tenant LoRA Serving
- LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
- DeepSeek-V3 Technical Report
- Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity
- MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool
- Serving Heterogeneous LoRA Adapters in Distributed LLM Inference Systems
- Mixtral of Experts
- LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design
- Hello Again! LLM-powered Personalized Agent for Long-term Dialogue
- Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security
- gpt-oss-120b & gpt-oss-20b Model Card
- DeepSpeed-MoE: Advancing Mixture-of-Experts Inference and Training to Power Next-Generation AI Scale
- Mixture-of-Experts Meets Instruction Tuning:A Winning Combination for Large Language Models
- S-LoRA: Serving Thousands of Concurrent LoRA Adapters
- ExpertWeave: Efficiently Serving Expert-Specialized Fine-Tuned Adapters at Scale
- Qwen3 Technical Report
- M+: Extending MemoryLLM with Scalable Long-Term Memory
- DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads
- LoRA-LiteE: A Computationally Efficient Framework for Chatbot Preference-Tuning
Related papers
- Programmable Probabilistic Computer with 1,000,000 p-bits
- BatchGen: An Architecture for Scalable and Efficient Batch Inference
- Seamless Reconfiguration for DAG-BFT (Technical Report)
- ELDR: Expert-Locality-Aware Decode Routing for PD-Disaggregated MoE Serving
- iScheduler: Reinforcement Learning-Driven Continual Optimization for Large-Scale Resource Investment Problems
- TIRx: A Unified Tile Primitive ML Compiler Across Heterogeneous Backends