Arrow Research search

Author name cluster

Inho Jeong

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers
2 author rows

Possible papers

2

NeurIPS Conference 2025 Conference Paper

HiFC: High-efficiency Flash-based KV Cache Swapping for Scaling LLM Inference

  • Inho Jeong
  • Sunghyeon Woo
  • Sol Namkung
  • Dongsuk Jeon

Large‑language‑model inference with long contexts often produces key–value (KV) caches whose footprint exceeds the capacity of high‑bandwidth memory on a GPU. Prior LLM inference frameworks such as vLLM mitigate this pressure by swapping KV cache pages to host DRAM. However, the high cost of large DRAM pools makes this solution economically unattractive. Although offloading to SSDs can be a cost-effective way to expand memory capacity relative to DRAM, conventional frameworks such as FlexGen experience a substantial throughput drop since the data path that routes SSD traffic through CPU to GPU is severely bandwidth-constrained. To overcome these limitations, we introduce HiFC, a novel DRAM‑free swapping scheme that enables direct access to SSD-resident memory with low latency and high effective bandwidth. HiFC stores KV pages in pseudo-SLC (pSLC) regions of commodity NVMe SSDs, sustaining high throughput under sequential I/O and improving write endurance by up to 8$\times$. Leveraging GPU Direct Storage, HiFC enables direct transfers between SSD and GPU, bypassing host DRAM and alleviating PCIe bottlenecks. HiFC employs fine-grained block mapping to confine writes to high-performance pSLC zones, stabilizing latency and throughput under load. HiFC achieves inference throughput comparable to DRAM-based swapping under diverse long-context workloads, such as NarrativeQA, while significantly lowering the memory expansion cost of a GPU server system by 4. 5$\times$ over three years.

PDF Details

ICLR Conference 2025 Conference Paper

PaCA: Partial Connection Adaptation for Efficient Fine-Tuning

  • Sunghyeon Woo
  • Sol Namkung
  • Sunwoo Lee 0005
  • Inho Jeong
  • Beomseok Kim
  • Dongsuk Jeon

Prior parameter-efficient fine-tuning (PEFT) algorithms reduce memory usage and computational costs of fine-tuning large neural network models by training only a few additional adapter parameters, rather than the entire model. However, the reduction in computational costs due to PEFT does not necessarily translate to a reduction in training time; although the computational costs of the adapter layers are much smaller than the pretrained layers, it is well known that those two types of layers are processed sequentially on GPUs, resulting in significant latency overhead. LoRA and its variants avoid this latency overhead by merging the low-rank adapter matrices with the pretrained weights during inference. However, those layers cannot be merged during training since the pretrained weights must remain frozen while the low-rank adapter matrices are updated continuously over the course of training. Furthermore, LoRA and its variants do not reduce activation memory, as the first low-rank adapter matrix still requires the input activations to the pretrained weights to compute weight gradients. To mitigate this issue, we propose **Pa**rtial **C**onnection **A**daptation (**PaCA**), which fine-tunes randomly selected partial connections within the pretrained weights instead of introducing adapter layers in the model. PaCA not only enhances training speed by eliminating the time overhead due to the sequential processing of the adapter and pretrained layers but also reduces activation memory since only partial activations, rather than full activations, need to be stored for gradient computation. Compared to LoRA, PaCA reduces training time by 22% and total memory usage by 16%, while maintaining comparable accuracy across various fine-tuning scenarios, such as fine-tuning on the MMLU dataset and instruction tuning on the Oasst1 dataset. PaCA can also be combined with quantization, enabling the fine-tuning of large models such as LLaMA3.1-70B. In addition, PaCA enables training with 23% longer sequence and improves throughput by 16\% on both NVIDIA A100 GPU and INTEL Gaudi2 HPU compared to LoRA. The code is available at [https://github.com/WooSunghyeon/paca](https://github.com/WooSunghyeon/paca).

Details
v2026.09.13