AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

PLoRA: Efficient Concurrent LoRA Training for Large Language Models

Minghao Yan, Zhuang Wang, Zhen Jia, Shivaram Venkataraman, Yida Wang

ICML 2026 · Large language models › Instruction and fine-tuning · approach: Calibration and knowledge in LLM tuning

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
pack multiple LoRA configs into one job (planner only, sequential execution) (ablation)PLoRA · Qwen2.5-3B/7B, 120 configsmakespan: around 1.8x reductionImproved
add optimized packed LoRA kernels (ablation)Sequential PLoRA · Qwen2.5-3B/7B, 120 configsmakespan: up to 3.93x further reductionImproved
use Max GPU (all 8 GPUs per job) instead of Min GPU (ablation)sequential LoRA baseline · Qwen2.5, 120 configsmakespanHurt
increase batch size from 1 to 4 (ablation)PLoRA throughput gain · Qwen2.5 job throughputspeedup over Min GPU: 12.8x at BS 1, smaller at larger BSMixed
search 120 LoRA configs instead of default config (ablation)LoRA fine-tuning · cola, Qwen2.5-3Baccuracy: 53.8 -> 77.2Improved
search 120 LoRA configs instead of default config (ablation)LoRA fine-tuning · gsm8k, Qwen2.5-7Baccuracy: 72.1 -> 79.8Improved
increase LoRA batch size (ablation)LoRA fine-tuning · mrpc/cola/wnli/gsm8k, Qwen2.5-7Baccuracy: up to 11.3% accuracy differenceHurt
vary learning rate (ablation)LoRA fine-tuning · cola, Qwen2.5-7Baccuracy: 14.2% max accuracy differenceMixed
vary LoRA rank (ablation)LoRA fine-tuning · cola, Qwen2.5-7Baccuracy: 13.1% max accuracy differenceMixed
vary LoRA alpha (ablation)LoRA fine-tuning · Qwen2.5-7Baccuracy: up to 5.9% max accuracy differenceMixed
apply mrpc best config to gsm8k (ablation)LoRA fine-tuning · Qwen2.5-3Baccuracy: -7.4%Hurt
transfer cola best config from 7B to 3B (ablation)LoRA fine-tuning · colaaccuracy: -3.6%Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy