arXiv:2608. 03579v1 Announce Type: cross Abstract: Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters.
arXiv:2607. 21074v1 Announce Type: new Abstract: Fine-tuning Vision Transformers (ViTs) with low-rank adapters (LoRA) promises better communication efficiency under federated setup, yet existing aggregation strategies face fundamental limitations.
arXiv:2608. 19800v1 Announce Type: cross Abstract: Low-Rank Adaptation (LoRA) is a prominent fine-tuning method for large models, achieving competitive performance with reduced memory overhead.
arXiv:2607. 11940v1 Announce Type: cross Abstract: As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging.
The paper introduces ISO-LoRA, an optimizer that improves rank utilization in Low‑Rank Adaptation (LoRA) by coupling factor updates through spectral descent on the induced tangent perturbation in weight space. Experiments on GPT‑2 adaptation show that standard optimizers like AdamW concentrate updates in a few singular directions, whereas ISO-LoRA distributes energy more evenly, leading to higher effective rank and better downstream performance across 0.1B‑7B models. The authors provide theoretical guarantees under a stylized spiked‑gradient model and demonstrate that ISO-LoRA consistently outperforms factor‑wise optimizers, especially at moderate‑to‑large LoRA ranks.
arXiv:2609.06072v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) of mixture-of-experts (MoE) models commonly attaches a separate low-rank adapter to each expert. This expert-w...
arXiv:2508. 02932v2 Announce Type: replace Abstract: Low-Rank Adaptation (LoRA) has gained popularity as a fine-tuning approach for Large Language Models (LLMs) due to its low resource requirements and good performance.
arXiv:2606. 13767v1 Announce Type: cross Abstract: Low-rank adaptation (LoRA) and its variants provide a memory- and compute-efficient alternative to full fine-tuning of pre-trained models.
arXiv:2602. 24044v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distributed serving systems where hundreds of adapters must be hosted concurrently.
arXiv:2605.07111v3 Announce Type: replace-cross Abstract: Recent literature on fine-tuning Large Language Models highlights a fundamental debate. While Full Fine-Tuning (FFT) provides greater represe...
arXiv:2601. 16991v3 Announce Type: replace-cross Abstract: Adapting large pre-trained language models to downstream tasks often entails fine-tuning millions of parameters or deploying costly dense weight updates, which hinders their use in resource-constrained environments.
EAServe introduces an encode-aware disaggregated serving framework for multimodal large language models (MLLMs), restructuring the traditional Prefill-Decode pipeline into a three-stage Encode-Prefill-Decode (EPD) system. By treating Encode as the control point, EAServe coordinates load‑adaptive micro‑batching, rate‑controlled offloading to prefill workers, and dynamic SM partitioning to balance GPU utilization across stages. Its Hybrid Auto Selection (HAS) layer optimizes GPU allocation, encode batch size, and offload ratio using capacity profiling and Bayesian optimization, achieving up to 4.3× higher goodput compared to NVIDIA Dynamo and 1.7× higher than vLLM on various MLLM architectures.
arXiv:2604. 26968v2 Announce Type: replace-cross Abstract: Key-value (KV) cache memory management is the primary bottleneck limiting throughput and cost-efficiency in large-scale GPU inference serving.