paper-with-me

홈 › Papers

Toward Reproducible Cross-Backend Compatibility for Deep Learning: A Configuration-First Framework with Three-Tier Verification

2025-08-29 · Zehua Li arxiv

This paper presents a configuration-first framework for evaluating cross-backend compatibility in deep learning systems deployed on CPU, GPU, and compiled runtimes. The framework decouples experiments from code using YAML, supports both library and repository models, and employs a three-tier verification protocol covering tensor-level closeness, activation alignment, and task-level metrics. Through 672 checks across multiple models and tolerance settings, we observe that 72.0% of runs pass, with most discrepancies occurring under stricter thresholds. Our results show that detection models and compiled backends are particularly prone to drift, often due to nondeterministic post-processing. We further demonstrate that deterministic adapters and selective fallbacks can substantially improve agreement without significant performance loss. To our knowledge, this is the first unified framework that systematically quantifies and mitigates cross-backend drift in deep learning, providing a reproducible methodology for dependable deployment across heterogeneous runtimes.

📄 PDF Abstract BibTeX arXiv:2509.06977

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

AlignTune: Modular Toolkit for Post-Training Alignment of Large Language Models

2026-02-10 · R E Zera Marveen Lyngkhoi, Chirag Chawla, Pratinav Seth, Utsav Avaiya 외 arxiv

Post-training alignment is central to deploying large language models (LLMs), yet practical workflows remain split across backend-specific tools and ad-hoc glue code, making experiments hard to reproduce. We identify bac…

Is Your NPU Ready for LLMs? Dissecting the Hidden Efficiency Bottlenecks in Mobile LLM Inference

2026-07-06 · Guanyu Cai, Ruiming Tian, Lang Yang, Zhouhong Ren 외 arxiv

Deploying Large Language Models (LLMs) on mobile devices enhances privacy and reduces latency, but is severely bottlenecked by hardware inefficiency. We present the first comprehensive, cross-layer measurement study of m…

Mind the Boundary: Stabilizing Gemini Enterprise A2A via a Cloud Run Hub Across Projects and Accounts

2026-01-26 · Takao Morita arxiv

Enterprise conversational UIs increasingly need to orchestrate heterogeneous backend agents and tools across project and account boundaries in a secure and reproducible way. Starting from Gemini Enterprise Agent-to-Agent…

Question AnsweringGeneral Knowledge

MemSecBench: Tracking Agent Memory Poisoning from Persistence to Consequence and Repair

2026-07-29 · Xuanze Chen, Xukang Xie, Wentao Fu, Jiajun Zhou 외 arxiv

Memory systems allow agents to retain and reuse information from past interactions, but they can also let malicious content persist. A malicious instruction crafted by an attacker may be stored in long-term memory, recal…

Dooly: Configuration-Agnostic, Redundancy-Aware Profiling for LLM Inference Simulation

2026-05-08 · Joon Ha Kim, Geon-Woo Kim, Anoop Rachakonda, Daehyeok Kim arxiv

Selecting the optimal LLM inference configuration requires evaluation across hardware, serving engines, attention backends, and model architectures, since no single choice performs best across all workloads. Profile-base…