Cover Image

ModeSwitch-LLM: A Lightweight Phase-Aware Controller for Cross-Mode LLM Inference on a Single GPU

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Sunesh, Aman, Alshehhi, Ali, Dhakne, Hivansh
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Computation and Language Performance
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Bench360: Benchmarking Local LLM Inference from 360 Degrees
by: Stuhlmann, Linus, et al.
Published: (2025)

ISO: Overlap of Computation and Communication within Seqenence For LLM Inference
by: Xiao, Bin, et al.
Published: (2024)

Characterizing WebGPU Dispatch Overhead for LLM Inference Across Four GPU Vendors, Three Backends, and Three Browsers
by: Maczan, Jędrzej
Published: (2026)

QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving
by: Lin, Yujun, et al.
Published: (2024)

Systematic Evaluation of Optimization Techniques for Long-Context Language Models
by: Ahmed, Ammar, et al.
Published: (2025)

KVPR: Efficient LLM Inference with I/O-Aware KV Cache Partial Recomputation
by: Jiang, Chaoyi, et al.
Published: (2024)

GreenServ: Energy-Efficient Context-Aware Dynamic Routing for Multi-Model LLM Inference
by: Ziller, Thomas, et al.
Published: (2026)

KVDirect: Distributed Disaggregated LLM Inference
by: Chen, Shiyang, et al.
Published: (2024)

Confidential LLM Inference: Performance and Cost Across CPU and GPU TEEs
by: Chrapek, Marcin, et al.
Published: (2025)

Model Compression and Efficient Inference for Large Language Models: A Survey
by: Wang, Wenxiao, et al.
Published: (2024)

KernelBenchX: A Comprehensive Benchmark for Evaluating LLM-Generated GPU Kernels
by: Wang, Han, et al.
Published: (2026)

Agentic Auto-Scheduling: An Experimental Study of LLM-Guided Loop Optimization
by: Merouani, Massinissa, et al.
Published: (2025)

CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing
by: Zheng, Wenhao, et al.
Published: (2025)

Enhancing Inference Efficiency of Large Language Models: Investigating Optimization Strategies and Architectural Innovations
by: Tyukin, Georgy
Published: (2024)

LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems
by: Wu, Siyu, et al.
Published: (2026)

An Inquiry into Datacenter TCO for LLM Inference with FP8
by: Kim, Jiwoo, et al.
Published: (2025)

Energy-Aware LLMs: A step towards sustainable AI for downstream applications
by: Tran, Nguyen Phuc, et al.
Published: (2025)

Blink: CPU-Free LLM Inference by Delegating the Serving Stack to GPU and SmartNIC
by: Siavashi, Mohammad, et al.
Published: (2026)

Forecasting GPU Performance for Deep Learning Training and Inference
by: Lee, Seonho, et al.
Published: (2024)

FLuRKA: Fast and accurate unified Low-Rank & Kernel Attention
by: Gupta, Ahan, et al.
Published: (2023)

Priority Sampling of Large Language Models for Compilers
by: Grubisic, Dejan, et al.
Published: (2024)

KIVI: A Tuning-Free Asymmetric 2bit Quantization for KV Cache
by: Liu, Zirui, et al.
Published: (2024)

Block Sparse Flash Attention
by: Ohayon, Daniel, et al.
Published: (2025)

AttentionEngine: A Versatile Framework for Efficient Attention Mechanisms on Diverse Hardware Platforms
by: Chen, Feiyang, et al.
Published: (2025)

REAM: Merging Improves Pruning of Experts in LLMs
by: Jha, Saurav, et al.
Published: (2026)

Glinthawk: A Two-Tiered Architecture for Offline LLM Inference
by: Hamadanian, Pouya, et al.
Published: (2025)

LServe: Efficient Long-sequence LLM Serving with Unified Sparse Attention
by: Yang, Shang, et al.
Published: (2025)

ZipServ: Fast and Memory-Efficient LLM Inference with Hardware-Aware Lossless Compression
by: Fan, Ruibo, et al.
Published: (2026)

Prism: Unleashing GPU Sharing for Cost-Efficient Multi-LLM Serving
by: Yu, Shan, et al.
Published: (2025)

MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference
by: Chu, Kexin, et al.
Published: (2026)

PARD: Accelerating LLM Inference with Low-Cost PARallel Draft Model Adaptation
by: An, Zihao, et al.
Published: (2025)

Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents
by: Zhang, Qizheng, et al.
Published: (2025)

TaxBreak: Unmasking the Hidden Costs of LLM Inference Through Overhead Decomposition
by: Vellaisamy, Prabhu, et al.
Published: (2026)

Accelerating Mobile Inference through Fine-Grained CPU-GPU Co-Execution
by: Li, Zhuojin, et al.
Published: (2025)

Performance Characterization of Expert Router for Scalable LLM Inference
by: Pichlmeier, Josef, et al.
Published: (2024)

GPU Kernel Optimization Beyond Full Builds: An LLM Framework with Minimal Executable Programs
by: Chu, Ruifan, et al.
Published: (2025)

The Illusion of Power Capping in LLM Decode: A Phase-Aware Energy Characterisation Across Attention Architectures
by: Ma, Bole, et al.
Published: (2026)

DyLLM: Efficient Diffusion LLM Inference via Saliency-based Token Selection and Partial Attention
by: Lee, Younjoo, et al.
Published: (2026)

Rudder: Steering Prefetching in Distributed GNN Training using LLM Agents
by: Sarkar, Aishwarya, et al.
Published: (2026)

PixelBrax: Learning Continuous Control from Pixels End-to-End on the GPU
by: McInroe, Trevor, et al.
Published: (2025)