paper-with-me

Papers

FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference

2025-10-26 · Divya Jyoti Bajpai, Manjesh Kumar Hanawal arxiv

Vision-language Models (VLMs) have made significant strides in visual understanding and query response generation, but often face challenges of high computational cost and inference latency due to autoregressive decoding. In this work, we introduce an imitation-learning-based Self-Speculative Decoding (SSD) framework, named FastVLM, to address these limitations. Our approach employs a lightweight draft model for token generation in an autoregressive manner, while a full model verifies these tokens non-autoregressively. Accepted tokens proceed seamlessly, while rejected tokens are corrected by the full model and used to guide the draft model's refinement. Through an imitation network, FastVLM enhances the draft model by integrating deeper level insights from the full model's architecture. Also, it maintains the performance integrity of the full model while training the draft model, achieving a balance between efficiency and accuracy. Our method speeds up the inference process by 1.55-1.85x as compared to the final layer with minimal loss in performance.

📄 PDF Abstract BibTeX arXiv:2510.22641

Code (0)

등록된 구현이 없습니다.

Tasks

Response Generation

Similar Papers 제목 키워드 기반

FastVLM: Efficient Vision Encoding for Vision Language Models

2024-12-17 · CVPR 2025 1 · Pavan Kumar Anasosalu Vasu, Fartash Faghri, Chun-Liang Li, Cem Koc 외

Scaling the input image resolution is essential for enhancing the performance of Vision Language Models (VLMs), particularly in text-rich image understanding tasks. However, popular visual encoders such as ViTs become in…

Speculative Speculative Decoding

2026-03-03 · Tanishq Kumar, Tri Dao, Avner May arxiv

Autoregressive decoding is bottlenecked by its sequential nature. Speculative decoding has become a standard way to accelerate inference by using a fast draft model to predict upcoming tokens from a slower target model, …

SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification

2025-09-26 · Kanghoon Yoon, Minsub Kim, Sungjae Lee, Joonhyung Lee 외 arxiv

Speculative decoding accelerates LLM inference by verifying candidate tokens from a draft model against a larger target model. Recent judge decoding boosts this process by relaxing verification criteria by accepting draf…

Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity

2024-10-01 · Michael R. Metel, Peng Lu, Boxing Chen, Mehdi Rezagholizadeh 외

We present a simple on the fly method for faster inference of large language models. Unlike other (self-)speculative decoding techniques, our method does not require fine-tuning or black-box optimization to generate a fi…

S3D: A Simple and Cost-Effective Self-Speculative Decoding Scheme for Low-Memory GPUs

2024-05-30 · Wei Zhong, Manasa Bharadwaj

Speculative decoding (SD) has attracted a significant amount of research attention due to the substantial speedup it can achieve for LLM inference. However, despite the high speedups they offer, speculative decoding meth…

GPUQuantization