Skip to content
conftrace_

self-speculative decoding

7 papers

Explore in graph

Also known as

SSD

Co-occurring keywords · papers mentioning both

inference acceleration (4) large language model (3) speculative decoding (3) model compression (3) multi-token prediction (2) language model (2) efficient inference (2) layer dropout (1) token generation (1) early exit inference (1)

Papers

Fast SceneScript: Fast and Accurate Language-Based 3D Scene Understanding via Multi-Token Prediction CVPR 2026 FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference IJCNLP 2025 FractalLLM: Lossless Self-Speculative Decoding with Layer Embedded Self-Compression EMNLP 2025 Pre-Training Curriculum for Multi-Token Prediction in Language Models ACL 2025 QuantSpec: Self-Speculative Decoding with Hierarchical Quantized KV Cache ICML 2025 Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity EMNLP 2024 LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding ACL 2024