Cover Image

QuickSilver -- Speeding up LLM Inference through Dynamic Token Halting, KV Skipping, Contextual Token Fusion, and Adaptive Matryoshka Quantization

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Khanna, Danush, Guru, Aditya Kumar, Sridhar, Srivarshinee, Ahmed, Zidan, Bahirwani, Rubhav, Malhotra, Meetu, Jain, Vinija, Chadha, Aman, Das, Amitava, Ghosh, Kripabandhu
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Artificial Intelligence I.2.0; I.2.7
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

SPHERICAL KV: Angle-Domain Attention and Rate-Distortion Retention for Efficient Long-Context Inference
by: Chauhan, Anay, et al.
Published: (2026)

ObfusQAte: A Proposed Framework to Evaluate LLM Robustness on Obfuscated Factual Question Answering
by: Ghosh, Shubhra, et al.
Published: (2025)

YETI (YET to Intervene) Proactive Interventions by Multimodal AI Agents in Augmented Reality Tasks
by: Bandyopadhyay, Saptarashmi, et al.
Published: (2025)

Differentiable Hierarchical Visual Tokenization
by: Aasan, Marius, et al.
Published: (2025)

Hierarchical Prompting Taxonomy: A Universal Evaluation Framework for Large Language Models Aligned with Human Cognitive Principles
by: Budagam, Devichand, et al.
Published: (2024)

From Next Token Prediction to (STRIPS) World Models
by: Núñez-Molina, Carlos, et al.
Published: (2025)

Future Token Prediction -- Causal Language Modelling with Per-Token Semantic State Vector for Multi-Token Prediction
by: Walker, Nicholas
Published: (2024)

Before the Last Token: Diagnosing Final-Token Safety Probe Failures
by: Doda, Shravan
Published: (2026)

Tokens with Meaning: A Hybrid Tokenization Approach for Turkish
by: Bayram, M. Ali, et al.
Published: (2025)

Learnings from Scaling Visual Tokenizers for Reconstruction and Generation
by: Hansen-Estruch, Philippe, et al.
Published: (2025)

Beyond Token Limits: Assessing Language Model Performance on Long Text Classification
by: Sebők, Miklós, et al.
Published: (2025)

Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
by: He, Langzhou, et al.
Published: (2026)

Matryoshka Policy Gradient for Entropy-Regularized RL: Convergence and Global Optimality
by: Ged, François, et al.
Published: (2023)

Hopscotch: Discovering and Skipping Redundancies in Language Models
by: Eyceoz, Mustafa, et al.
Published: (2025)

Super Apriel: One Checkpoint, Many Speeds
by: Labs, SLAM, et al.
Published: (2026)

Cross-Layer Cache Aggregation for Token Reduction in Ultra-Fine-Grained Image Recognition
by: Rios, Edwin Arkel, et al.
Published: (2024)

LaTIM: Measuring Latent Token-to-Token Interactions in Mamba Models
by: Pitorro, Hugo, et al.
Published: (2025)

BlankSkip: Early-exit Object Detection onboard Nano-drones
by: Marra, Carlo, et al.
Published: (2026)

On the Limits of Learned Importance Scoring for KV Cache Compression
by: Steele, Brady
Published: (2026)

Reducing Object Hallucination in LVLMs via Emphasizing Image-negative Tokens
by: Shen, Meng, et al.
Published: (2026)

iTrash: Incentivized Token Rewards for Automated Sorting and Handling
by: Ortega, Pablo, et al.
Published: (2025)

Tokenizing Motion: A Generative Approach for Scene Dynamics Compression
by: Yin, Shanzhi, et al.
Published: (2024)

Next Token Prediction Is a Dead End for Creativity
by: Olatunji, Ibukun, et al.
Published: (2025)

Almost Linear Time Consistent Mode Estimation and Quick Shift Clustering
by: Hashemian, Sajjad
Published: (2025)

Dense Video Understanding with Gated Residual Tokenization
by: Zhang, Haichao, et al.
Published: (2025)

Pre-trained Models Perform the Best When Token Distributions Follow Zipf's Law
by: He, Yanjin, et al.
Published: (2025)

Kronecker Embeddings: Byte-Level Structured Token Representations for Parameter-Efficient Language Models
by: Shravan, Rohan
Published: (2026)

All for One: LLMs Solve Mental Math at the Last Token With Information Transferred From Other Tokens
by: Mamidanna, Siddarth, et al.
Published: (2025)

BitSkip: An Empirical Analysis of Quantization and Early Exit Composition in Transformers
by: Bhuvaneswaran, Ramshankar, et al.
Published: (2025)

High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models
by: He, Mengqi, et al.
Published: (2025)

EvoPrune: Early-Stage Visual Token Pruning for Efficient MLLMs
by: Chen, Yuhao, et al.
Published: (2026)

Lost in Latent Space: Disentangled Models and the Challenge of Combinatorial Generalisation
by: Montero, Milton L., et al.
Published: (2022)

The Battle of LLMs: A Comparative Study in Conversational QA Tasks
by: Rangapur, Aryan, et al.
Published: (2024)

Good to Go: The LOOP Skill Engine That Hits 99% Success and Slashes Token Usage by 99% via One-Shot Recording and Deterministic Replay
by: Wang, Xiaohua, et al.
Published: (2026)

LRCP: Low-Rank Compressibility Guided Visual Token Pruning for Efficient LVLMs
by: Lu, Hongyu, et al.
Published: (2026)

VQToken: Neural Discrete Token Representation Learning for Extreme Token Reduction in Video Large Language Models
by: Zhang, Haichao, et al.
Published: (2025)

Tokenization Standards for Linguistic Integrity: Turkish as a Benchmark
by: Bayram, M. Ali, et al.
Published: (2025)

AraToken: Optimizing Arabic Tokenization with Normalization Pipeline and Language Extension for Qwen3
by: Kashirskiy, Mark, et al.
Published: (2025)

Improving Angular Speed Uniformity by Piecewise Radical Reparameterization
by: Hong, Hoon, et al.
Published: (2024)

KL-Regularised Q-Learning: A Token-level Action-Value perspective on Online RLHF
by: Brown, Jason R, et al.
Published: (2025)