REVIEW 5 cited by
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Compress then Serve: Serving Thousands of LoRA Adapters with Little Overhead
read the original abstract
Fine-tuning large language models (LLMs) with low-rank adaptations (LoRAs) has become common practice, often yielding numerous copies of the same LLM differing only in their LoRA updates. This paradigm presents challenges for systems that serve real-time responses to queries that each involve a different LoRA. Prior works optimize the design of such systems but still require continuous loading and offloading of LoRAs, as it is infeasible to store thousands of LoRAs in GPU memory. To mitigate this issue, we investigate the efficacy of compression when serving LoRAs. We propose a method for the joint compression of LoRAs into a shared basis paired with LoRA-specific scaling matrices. We extend our algorithm to learn clusters of LoRAs that are amenable to joint compression, allowing it to scale gracefully to large LoRA collections. Our experiments with up to 1000 LoRAs demonstrate that compressed LoRAs preserve performance while offering major throughput gains in realistic serving scenarios with over a thousand LoRAs, maintaining 80% of the throughput of serving a single LoRA.
Forward citations
Cited by 5 Pith papers
-
Learning Only What Valid Adapters Can Express: Subspace-Constrained Adaptation Against Fine-Tuning Poisoning
Restricting LoRA fine-tuning to the subspace of 196 trusted adapters blocks label-inversion poisoning and provides a built-in OOD signal, at the cost of a plasticity ceiling on poorly-covered tasks.
-
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
MinT enables efficient management of million-scale LoRA-adapted LLM policies over shared 1T-parameter base models by moving only small adapters through training and serving pipelines.
-
Learn-To-Learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM
A hypernetwork generates meta-gating parameters for SwiGLU blocks to let LLMs adapt their nonlinearity to arbitrary textual conditions, outperforming finetuning and meta-learning baselines with reasonable generalizati...
-
MinT: Managed Infrastructure for Training and Serving Millions of LLMs
MinT is a system for managing million-scale LoRA adapter catalogs on shared 1T-parameter base models, with reported efficiency gains in adapter movement, multi-policy training, and catalog addressability.
-
Learn-To-Learn on Arbitrary Textual Conditioning: A Hypernetwork-Driven Meta-Gated LLM
A hypernetwork produces a condition-dependent beta that meta-gates SwiGLU nonlinearity, giving LLMs adaptive behavior across task, domain, persona and style inputs without finetuning.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.