Buchumschlag

Unveiling Environmental Impacts of Large Language Model Serving: A Functional Unit View

Fuente: arXiv

Gespeichert in:

Bibliographische Detailangaben
Hauptverfasser:	Wu, Yanran, Hua, Inez, Ding, Yi
Format:	Preprint
Veröffentlicht:	2025
Schlagworte:	Machine Learning Hardware Architecture Computation and Language
Online-Zugang:	Acceder al recurso
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Ähnliche Einträge

Not All Water Consumption Is Equal: A Water Stress Weighted Metric for Sustainable Computing
von: Wu, Yanran, et al.
Veröffentlicht: (2025)

HDLxGraph: Bridging Large Language Models and HDL Repositories via HDL Graph Databases
von: Zheng, Pingqing, et al.
Veröffentlicht: (2025)

GreenLLM: Disaggregating Large Language Model Serving on Heterogeneous GPUs for Lower Carbon Emissions
von: Shi, Tianyao, et al.
Veröffentlicht: (2024)

OPAL: Outlier-Preserved Microscaling Quantization Accelerator for Generative Large Language Models
von: Koo, Jahyun, et al.
Veröffentlicht: (2024)

Basis Selection: Low-Rank Decomposition of Pretrained Large Language Models for Target Applications
von: Li, Yang, et al.
Veröffentlicht: (2024)

DeepRTL2: A Versatile Model for RTL-Related Tasks
von: Liu, Yi, et al.
Veröffentlicht: (2025)

Pimba: A Processing-in-Memory Acceleration for Post-Transformer Large Language Model Serving
von: Kim, Wonung, et al.
Veröffentlicht: (2025)

DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model
von: Liu, Yi, et al.
Veröffentlicht: (2025)

MX+: Pushing the Limits of Microscaling Formats for Efficient Large Language Model Serving
von: Lee, Jungi, et al.
Veröffentlicht: (2025)

PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models
von: Cho, Eunyeong, et al.
Veröffentlicht: (2026)

Llumnix: Dynamic Scheduling for Large Language Model Serving
von: Sun, Biao, et al.
Veröffentlicht: (2024)

Understanding the Potential of FPGA-Based Spatial Acceleration for Large Language Model Inference
von: Chen, Hongzheng, et al.
Veröffentlicht: (2023)

Speculative Decoding for Verilog: Speed and Quality, All in One
von: Xu, Changran, et al.
Veröffentlicht: (2025)

Characterizing the Behavior of Training Mamba-based State Space Models on GPUs
von: Baruah, Trinayan, et al.
Veröffentlicht: (2025)

Scaling Laws for Floating Point Quantization Training
von: Sun, Xingwu, et al.
Veröffentlicht: (2025)

Is Finer Better? The Limits of Microscaling Formats in Large Language Models
von: Fasoli, Andrea, et al.
Veröffentlicht: (2026)

D2S-FLOW: Automated Parameter Extraction from Datasheets for SPICE Model Generation Using Large Language Models
von: Chen, Hong Cai, et al.
Veröffentlicht: (2025)

Leveraging High-Level Synthesis and Large Language Models to Generate, Simulate, and Deploy a Uniform Random Number Generator Hardware Design
von: Meech, James T.
Veröffentlicht: (2023)

Serving Large Language Models on Huawei CloudMatrix384
von: Zuo, Pengfei, et al.
Veröffentlicht: (2025)

Ultra Memory-Efficient On-FPGA Training of Transformers via Tensor-Compressed Optimization
von: Tian, Jiayi, et al.
Veröffentlicht: (2025)

Understanding and Mitigating Errors of LLM-Generated RTL Code
von: Zhang, Jiazheng, et al.
Veröffentlicht: (2025)

From Loop Nests to Silicon: Mapping AI Workloads onto AMD NPUs with MLIR-AIR
von: Wang, Erwei, et al.
Veröffentlicht: (2025)

Orion: Characterizing and Programming Apple's Neural Engine for LLM Training and Inference
von: Kumaresan, Ramchand
Veröffentlicht: (2026)

GRPO with State Mutations: Improving LLM-Based Hardware Test Plan Generation
von: Kochar, Dimple Vijay, et al.
Veröffentlicht: (2026)

Hardwired-Neurons Language Processing Units as General-Purpose Cognitive Substrates
von: Liu, Yang, et al.
Veröffentlicht: (2025)

Memory Access Characterization of Large Language Models in CPU Environment and its Potential Impacts
von: Banasik, Spencer
Veröffentlicht: (2025)

Chameleon: a Heterogeneous and Disaggregated Accelerator System for Retrieval-Augmented Language Models
von: Jiang, Wenqi, et al.
Veröffentlicht: (2023)

Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective
von: Li, Jinhao, et al.
Veröffentlicht: (2024)

GFormer: Accelerating Large Language Models with Optimized Transformers on Gaudi Processors
von: Zhang, Chengming, et al.
Veröffentlicht: (2024)

HaLoRA: Hardware-aware Low-Rank Adaptation for Large Language Models Based on Hybrid Compute-in-Memory Architecture
von: Wu, Taiqiang, et al.
Veröffentlicht: (2025)

Guaranteed Guess: A Language Modeling Approach for CISC-to-RISC Transpilation with Testing Guarantees
von: Heakl, Ahmed, et al.
Veröffentlicht: (2025)

Lorecast: Layout-Aware Performance and Power Forecasting from Natural Language
von: Wang, Runzhi, et al.
Veröffentlicht: (2025)

FP6-LLM: Efficiently Serving Large Language Models Through FP6-Centric Algorithm-System Co-Design
von: Xia, Haojun, et al.
Veröffentlicht: (2024)

LLM-VeriPPA: Power, Performance, and Area Optimization aware Verilog Code Generation with Large Language Models
von: Thorat, Kiran, et al.
Veröffentlicht: (2025)

LowRA: Accurate and Efficient LoRA Fine-Tuning of LLMs under 2 Bits
von: Zhou, Zikai, et al.
Veröffentlicht: (2025)

Non-Monotonic Latency in Apple MPS Decoding: KV Cache Interactions and Execution Regimes
von: Hendria, Willy Fitra
Veröffentlicht: (2026)

Allo: A Programming Model for Composable Accelerator Design
von: Chen, Hongzheng, et al.
Veröffentlicht: (2024)

Dato: A Task-Based Programming Model for Dataflow Accelerators
von: Fang, Shihan, et al.
Veröffentlicht: (2025)

From Principles to Practice: A Systematic Study of LLM Serving on Multi-core NPUs
von: Zhu, Tianhao, et al.
Veröffentlicht: (2025)

COMET: Towards Partical W4A4KV4 LLMs Serving
von: Liu, Lian, et al.
Veröffentlicht: (2024)