CoA-LoRA trains a single configuration-aware model on a Pareto-optimized set of quantization configurations to enable dynamic LoRA adaptation to arbitrary bit-width assignments without per-configuration fine-tuning.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
On-the-Fly Adaptation to Quantization: Configuration-Aware LoRA for Efficient Fine-Tuning of Quantized LLMs
CoA-LoRA trains a single configuration-aware model on a Pareto-optimized set of quantization configurations to enable dynamic LoRA adaptation to arbitrary bit-width assignments without per-configuration fine-tuning.