mlsanityData to 14 Oct 2026

HADES: Hardware Accelerated Decoding for Efficient Speculation in Large Language Models

arXiv 2412.19925 ↗First posted 27 Dec 2024cs.CL cs.AI cs.ARcited by 15

On the map: Efficient LLM inference and serving → Speculative decoding

Abstract (arXiv)

Large Language Models (LLMs) have revolutionized natural language processing by understanding and generating human-like text. However, the increasing demand for more sophisticated LLMs presents significant computational challenges due to their scale and complexity. This paper introduces Hardware Accelerated Decoding (HADES), a novel approach to enhance the performance and energy efficiency of LLMs. We address the design of an LLM accelerator with hardware-level speculative decoding support, a concept not previously explored in existing literature. Our work demonstrates how speculative decoding can significantly improve the efficiency of LLM operations, paving the way for more advanced and practical applications of these models.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Placed in Speculative decoding, one of 12 directions in Efficient LLM inference and serving. Builds on 16 of its 25 references that are in the map. First posted on arXiv 27 Dec 2024.

Builds on

16 of 25 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Cascade Speculative Drafting for Even Faster LLM Inference18 Dec
  2. 2023SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification16 May
  3. 2023Accelerating Large Language Model Decoding with Speculative Sampling2 Feb
  4. 2022Fast Inference from Transformers via Speculative Decoding30 Nov

Other references · 12

  1. 2017Attention Is All You Needcited by 60,361
  2. 2020Language Models are Few-Shot Learnerscited by 32,419
  3. 2024The Llama 3 Herd of Modelscited by 14,715
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  6. 2016Quantized Neural Networks: Training Neural Networks with Low Precision Weights and Activationscited by 426
  7. 2020Why should we add early exits to neural networks?cited by 70
  8. 2024A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Healthcited by 24
  9. 2023SwiftTron: An Efficient Hardware Accelerator for Quantized Transformerscited by 18
  10. 2023BRAINTEASER: Lateral Thinking Puzzles for Large Language Modelscited by 18
  11. 2024LlamaF: An Efficient Llama2 Architecture Accelerator on Embedded FPGAscited by 12
  12. 2024A Consolidated Volatility Prediction with Back Propagation Neural Network and Genetic Algorithmcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 14; 2026: 1.

15 papers.

Sort:

By area:

  1. 2025From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agentcited by 33
  2. 2025Cloud-Based AI Systems: Leveraging Large Language Models for Intelligent Fault Detection and Autonomous Self-Healingcited by 10
  3. 2025Data Augmentation Through Random Style Replacementcited by 9
  4. 2025Cross-Cloud Data Privacy Protection: Optimizing Collaborative Mechanisms of AI Systems by Integrating Federated Learning and LLMscited by 9
  5. 2025Bias Evaluation and Mitigation in Retrieval-Augmented Medical Question-Answering Systemscited by 6
  6. 2025A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyondcited by 6
  7. 2025Instruction Tuning and CoT Prompting for Contextual Medical QA with LLMscited by 5
  8. 2025Exploring Reasoning-Infused Text Embedding with Large Language Models for Zero-Shot Dense Retrievalcited by 2
  9. 2025Anomaly Detection and Early Warning Mechanism for Intelligent Monitoring Systems in Multi-Cloud Environments Based on LLMcited by 1
  10. 2025Federated Learning-Based Data Collaboration Method for Enhancing Edge Cloud AI System Security Using Large Language Modelscited by 1
  11. 2025E-bike agents: Large Language Model-Driven E-Bike Accident Analysis and Severity Predictioncited by 0
  12. 2025An Intelligent Fault Self-Healing Mechanism for Cloud AI Systems via Integration of Large Language Models and Deep Reinforcement Learningcited by 0
3 more
  1. 2025Leveraging Large Language Model for Intelligent Log Processing and Autonomous Debugging in Cloud AI Platformscited by 0
  2. 2025Cognitive Load Traces as Symbolic and Visual Accounts of Deep Model Cognitioncited by 0
  3. 2026Safe and Adaptive Cloud Healing: Verifying LLM-Generated Recovery Plans with a Neural-Symbolic World Modelcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2023Accelerating LLM Inference with Staged Speculative Decoding
  2. 2023The Synergy of Speculative Decoding and Batching in Serving Large Language Models
  3. 2024Unlocking Efficiency in Large Language Model Inference: A Comprehensive Survey of Speculative Decoding
  4. 2024Decoding Speculative Decoding
  5. 2024Beyond the Speculative Game: A Survey of Speculative Execution in Large Language Models
  6. 2026SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
  7. 2024Hardware-Aware Parallel Prompt Decoding for Memory-Efficient Acceleration of LLM Inference
  8. 2024SSSD: Simply-Scalable Speculative Decoding