paper-with-me

홈 › Papers

From Theory to Throughput: CUDA-Optimized APML for Large-Batch 3D Learning

2025-12-17 · Sasan Sharifipour, Constantino Álvarez Casado, Manuel Lage Cañellas, Miguel Bordallo López arxiv

Loss functions are fundamental to learning accurate 3D point cloud models, yet common choices trade geometric fidelity for computational cost. Chamfer Distance is efficient but permits many-to-one correspondences, while Earth Mover Distance better reflects one-to-one transport at high computational cost. APML approximates transport with differentiable Sinkhorn iterations and an analytically derived temperature, but its dense formulation scales quadratically in memory. We present CUDA-APML, a sparse GPU implementation that thresholds negligible assignments and runs adaptive softmax, bidirectional symmetrization, and Sinkhorn normalization directly in COO form. This yields near-linear memory scaling and preserves gradients on the stored support, while pairwise distance evaluation remains quadratic in the current implementation. On ShapeNet and MM-Fi, CUDA-APML matches dense APML within a small tolerance while reducing peak GPU memory by 99.9%. Code available at: https://github.com/Multimodal-Sensing-Lab/apml

📄 PDF Abstract BibTeX arXiv:2512.19743

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Productively Deploying Emerging Models on Emerging Platforms: A Top-Down Approach for Testing and Debugging

2024-04-14 · Siyuan Feng, Jiawei Liu, Ruihang Lai, Charlie F. Ruan 외

While existing machine learning (ML) frameworks focus on established platforms, like running CUDA on server-grade GPUs, there have been growing demands to enable emerging AI applications in a broader set of scenarios, su…

SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining

2026-02-11 · Yifan Zhang, Zunhai Su, Shuhao Hu, Rui Yang 외 arxiv

While FP8 attention has shown substantial promise in innovations like FlashAttention-3, its integration into the decoding phase of the DeepSeek Multi-head Latent Attention (MLA) architecture presents notable challenges. …

SIP: Autotuning GPU Native Schedules via Stochastic Instruction Perturbation

2024-03-25 · Guoliang He, Eiko Yoneki

Large language models (LLMs) have become a significant workload since their appearance. However, they are also computationally expensive as they have billions of parameters and are trained with massive amounts of data. T…

GPU

QUICK: Quantization-aware Interleaving and Conflict-free Kernel for efficient LLM inference

2024-02-15 · Taesu Kim, Jongho Lee, Daehyun Ahn, Sarang Kim 외

We introduce QUICK, a group of novel optimized CUDA kernels for the efficient inference of quantized Large Language Models (LLMs). QUICK addresses the shared memory bank-conflict problem of state-of-the-art mixed precisi…

GPUQuantization

CuAsmRL: Optimizing GPU SASS Schedules via Deep Reinforcement Learning

2025-01-14 · Guoliang He, Eiko Yoneki

Large language models (LLMs) are remarked by their substantial computational requirements. To mitigate the cost, researchers develop specialized CUDA kernels, which often fuse several tensor operations to maximize the ut…

Deep Reinforcement LearningGPUreinforcement-learningReinforcement Learning+1