Cover Image

Quasar: Quantized Self-Speculative Acceleration for Rapid Inference via Memory-Efficient Verification

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Huang, Guang, Wen, Zeyi
Format:	Preprint
Published:	2026
Subjects:	Distributed, Parallel, and Cluster Computing Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Collaborative Speculative Inference for Efficient LLM Inference Serving
by: Gao, Luyao, et al.
Published: (2025)

SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification
by: Miao, Xupeng, et al.
Published: (2023)

PipeInfer: Accelerating LLM Inference using Asynchronous Pipelined Speculation
by: Butler, Branden, et al.
Published: (2024)

MoE-SpeQ: Speculative Quantized Decoding with Proactive Expert Prefetching and Offloading for Mixture-of-Experts
by: Wang, Wenfeng, et al.
Published: (2025)

Accelerate Intermittent Deep Inference
by: Zhang, Ziliang
Published: (2024)

Accelerating OpenPangu Inference on NPU via Speculative Decoding
by: Dai, Yuntao, et al.
Published: (2026)

Efficient Data Distribution Estimation for Accelerated Federated Learning
by: Wang, Yuanli, et al.
Published: (2024)

HACK: Homomorphic Acceleration via Compression of the Key-Value Cache for Disaggregated LLM Inference
by: Zhang, Zeyu, et al.
Published: (2025)

Pie: Pooling CPU Memory for LLM Inference
by: Xu, Yi, et al.
Published: (2024)

ReSpec: Towards Optimizing Speculative Decoding in Reinforcement Learning Systems
by: Chen, Qiaoling, et al.
Published: (2025)

eMoE: Task-aware Memory Efficient Mixture-of-Experts-Based (MoE) Model Inference
by: Tairin, Suraiya, et al.
Published: (2025)

SHARe-KAN: Post-Training Vector Quantization for Cache-Resident KAN Inference
by: Smith, Jeff
Published: (2025)

AMUSD: Asynchronous Multi-Device Speculative Decoding for LLM Acceleration
by: McDanel, Bradley
Published: (2024)

Untied Ulysses: Memory-Efficient Context Parallelism via Headwise Chunking
by: Ghadia, Ravi, et al.
Published: (2026)

AutoChunk: Automated Activation Chunk for Memory-Efficient Long Sequence Inference
by: Zhao, Xuanlei, et al.
Published: (2024)

MorphServe: Efficient and Workload-Aware LLM Serving via Runtime Quantized Layer Swapping and KV Cache Resizing
by: Su, Zhaoyuan, et al.
Published: (2025)

Energy-Efficient Quantized Federated Learning for Resource-constrained IoT devices
by: Compaoré, Wilfrid Sougrinoma, et al.
Published: (2025)

MobiZO: Enabling Efficient LLM Fine-Tuning at the Edge via Inference Engines
by: Gao, Lei, et al.
Published: (2024)

DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models
by: Huang, You-Liang, et al.
Published: (2026)

SP-MoE: Speculative Decoding and Prefetching for Accelerating MoE-based Model Inference
by: Chen, Liangkun, et al.
Published: (2025)

GPU-Accelerated Optimization of Transformer-Based Neural Networks for Real-Time Inference
by: Mukherjee, Soutrik, et al.
Published: (2026)

Mind the Memory Gap: Unveiling GPU Bottlenecks in Large-Batch LLM Inference
by: Recasens, Pol G., et al.
Published: (2025)

Accelerating Large Language Model Training with 4D Parallelism and Memory Consumption Estimator
by: Fujii, Kazuki, et al.
Published: (2024)

Efficient Unified Caching for Accelerating Heterogeneous AI Workloads
by: Wang, Tianze, et al.
Published: (2025)

Communication-Efficient Federated Learning by Quantized Variance Reduction for Heterogeneous Wireless Edge Networks
by: Wang, Shuai, et al.
Published: (2025)

LLM-42: Enabling Determinism in LLM Inference with Verified Speculation
by: Gond, Raja, et al.
Published: (2026)

Arctic Inference with Shift Parallelism: Fast and Efficient Open Source Inference System for Enterprise AI
by: Rajbhandari, Samyam, et al.
Published: (2025)

Occult: Optimizing Collaborative Communication across Experts for Accelerated Parallel MoE Training and Inference
by: Luo, Shuqing, et al.
Published: (2025)

HybriMoE: Hybrid CPU-GPU Scheduling and Cache Management for Efficient MoE Inference
by: Zhong, Shuzhang, et al.
Published: (2025)

Dynamic Rebatching for Efficient Early-Exit Inference with DREX
by: Liu, Xuting, et al.
Published: (2025)

FlashEvolve: Accelerating Agent Self-Evolution with Asynchronous Stage Orchestration
by: Hu, Zhengding, et al.
Published: (2026)

Minions: Accelerating Large Language Model Inference with Aggregated Speculative Execution
by: Wang, Siqi, et al.
Published: (2024)

Accelerating Mixture-of-Experts Inference by Hiding Offloading Latency with Speculative Decoding
by: Wang, Zhibin, et al.
Published: (2025)

SPIN: Accelerating Large Language Model Inference with Heterogeneous Speculative Models
by: Chen, Fahao, et al.
Published: (2025)

Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference
by: Timor, Nadav, et al.
Published: (2024)

FloatSOM: GPU-Accelerated, Distributed, Topology-Flexible Self-Organizing Maps
by: Xu, Tony, et al.
Published: (2026)

FDC: Fast KV Dimensionality Compression for Efficient LLM Inference
by: Zhang, Zeyu, et al.
Published: (2024)

PecSched: Preemptive and Efficient Cluster Scheduling for LLM Inference
by: Zhang, Zeyu, et al.
Published: (2024)

Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference
by: Prabhakar, Rohan Baskar, et al.
Published: (2024)

SwiftSpec: Ultra-Low Latency LLM Decoding by Scaling Asynchronous Speculative Decoding
by: Zhang, Ziyi, et al.
Published: (2025)