POLAR formulates joint LoRA adapter caching and routing as a two-timescale contextual bandit, achieving sublinear regret bounds and outperforming non-adaptive baselines in experiments with real adapters.
hub
S-lora: Serving thousands of concurrent lora adapters
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
hub tools
citation-role summary
background 4
citation-polarity summary
roles
background 4polarities
background 4representative citing papers
InfiniLoRA decouples LoRA execution from base-model inference and reports 3.05x higher request throughput plus 54% more adapters meeting strict latency SLOs.
ALTO accelerates LoRA tuning up to 13.8x by monitoring loss trajectories for early stopping, using fused grouped GEMM with rank-local adapter parallelism, and combining intra- and inter-task scheduling for heterogeneous workloads without quality loss.
GaLore performs full-parameter LLM training with up to 65.5% less optimizer memory by projecting gradients onto a low-rank subspace at each step, matching full-rank performance on LLaMA pre-training and RoBERTa fine-tuning.
Prefill-only adaptation of LLMs yields 1.9x higher throughput for 512 adapters on Llama 3.1 70B with near-parity performance on RL tasks and recoverable loss on SFT.
Dr. Post-Training reframes general data as a data-induced regularizer for LLM post-training updates, yielding a family of methods that outperform data-selection baselines on SFT, RLHF, and RLVR tasks.
A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.
ForkKV uses copy-on-write disaggregated KV cache with DualRadixTree and ResidualAttention kernels to deliver up to 3x throughput over prior multi-LoRA serving systems with negligible quality loss.
CeRA overcomes LoRA's linear ceiling by injecting non-linear SiLU gating and dropout, outperforming high-rank LoRA on complex math reasoning with 1/8 the parameters.
LoRA-Mixer routes modular LoRA experts into attention projection matrices with an adaptive Routing Specialization Loss to improve multi-task performance while using fewer trainable parameters than prior LoRA-MoE methods.
FlexPipe introduces runtime pipeline refactoring for LLMs to achieve higher resource efficiency and lower latency in serverless GPU clusters with fragmentation.
HFX jointly designs scheduling and scaling for multi-SLO LLM serving, achieving up to 4.44x higher SLO attainment, 65.82% lower latency, and 49.81% lower cost than prior systems on multi-task workloads.
A comprehensive survey of PEFT algorithms for large models, covering their performance, overhead, applications, and real-world system implementations.
citing papers explorer
-
Separable Expert Architecture: Toward Privacy-Preserving LLM Personalization via Composable Adapters and Deletable User Proxies
A separable expert architecture uses base models, LoRA adapters, and deletable per-user proxies to enable privacy-preserving personalization and deterministic unlearning in LLMs.