Scaling DoRA: High-Rank Adaptation via Factored Norms and Fused Kernels
Weight-Decomposed Low-Rank Adaptation (DoRA) extends LoRA by decoupling weight magnitude from direction, but its forward pass requires the row-wise norm of W + sBA, a computation that every major framework we surveyed implements by materializing the dense [d_out, d_in] product BA. At d_in = 8192 and rank r = 384, a single module's norm requires about 512 MB of transient working memory in bf16, making high-rank DoRA costly and often infeasible on common single-GPU setups once hundreds of adapted modules and checkpointing are involved. We present two systems contributions. A factored norm decomposes the squared norm into base, cross, and Gram terms computable through O(d_out r + r^2) intermediates, eliminating the dense product. Fused Triton kernels collapse the four-kernel DoRA composition into a single pass, reducing memory traffic by about 4x and using a numerically stable form that avoids catastrophic cancellation in the near-unity rescaling regime where magnitude scales concentrate in practice. Across six 8-32B vision-language models (VLMs) on three NVIDIA GPUs (RTX 6000 PRO, H200, B200) at r = 384 in bf16, the fused implementation is 1.5-2.0x faster than Hugging Face PEFT's DoRA implementation for inference and 1.5-1.9x faster for gradient computation (optimizer step excluded), with up to 7 GB lower peak VRAM. Microbenchmarks on six GPUs spanning four architecture generations (L40S, A100, RTX 6000 PRO, H200, B200, B300) confirm 1.5-2.7x compose-kernel speedup. Final-logit cosine similarity exceeds 0.9999 across all model/GPU pairs, and multi-seed training curves match within 7.1 x 10^-4 mean per-step loss delta over 2000 steps.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
RoRA: Efficient Fine-Tuning of LLM with Reliability Optimization for Rank Adaptation
Fine-tuning helps large language models (LLM) recover degraded information and enhance task performance. Although Low-Rank Adaptation (LoRA) is widely used and effective for fine-tuning, we have observed that its scaling…
TemporalDoRA: Temporal PEFT for Robust Surgical Video Question Answering
Surgical Video Question Answering (VideoQA) requires accurate temporal grounding while remaining robust to natural variation in how clinicians phrase questions, where linguistic bias can arise. Standard Parameter Efficie…
Video Question AnsweringEDoRA: Efficient Weight-Decomposed Low-Rank Adaptation via Singular Value Decomposition
Parameter-efficient fine-tuning methods, such as LoRA, reduces the number of trainable parameters. However, they often suffer from scalability issues and differences between their learning pattern and full fine-tuning. T…
parameter-efficient fine-tuningDoRAN: Stabilizing Weight-Decomposed Low-Rank Adaptation via Noise Injection and Auxiliary Networks
Parameter-efficient fine-tuning (PEFT) methods have become the standard paradigm for adapting large-scale models. Among these techniques, Weight-Decomposed Low-Rank Adaptation (DoRA) has been shown to improve both the le…
parameter-efficient fine-tuningDoRA: Enhancing Parameter-Efficient Fine-Tuning with Dynamic Rank Distribution
Fine-tuning large-scale pre-trained models is inherently a resource-intensive task. While it can enhance the capabilities of the model, it also incurs substantial computational costs, posing challenges to the practical a…
parameter-efficient fine-tuning