conftrace_

draft model

21 papers

Explore in graph

Co-occurring keywords

speculative decoding (111) large language model (13587) inference acceleration (244) inference optimization (219) target model (10) model compression (3302) token generation (47) language model (4599) model acceleration (80) autoregressive decoding (33)

Papers

HCSpec: Two-Tier Horizontal Cascade Speculative Decoding for High-Efficiency Large Language Model Inference ACL 2026
Double: Breaking the Acceleration Limit via Double Retrieval Speculative Parallelism ACL 2026
An Empirical Study of Speculative Decoding for Small Language Models EACL 2026
EDSD: Entropy-Driven Design for Faster Speculative Decoding ACL 2026
SSSD: Simply-Scalable Speculative Decoding ACL 2026
Hierarchical Speculative Decoding with Dynamic Window NAACL 2025
Faster Speculative Decoding via Effective Draft Decoder with Pruned Candidate Tree ACL 2025
FastDraft: How to Train Your Draft ACL 2025
FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling ACL 2025
RASD: Retrieval-Augmented Speculative Decoding ACL 2025
Speculative Streaming: Efficient and Scalable Speculative Decoding with Multi-Stream Attention EMNLP 2025
FastVLM: Self-Speculative Decoding for Fast Vision-Language Model Inference IJCNLP 2025
Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation EMNLP 2025
A Drop-In Solution for On-the-Fly Adaptation of Speculative Decoding in Large Language Models ACL 2025
Decoding Speculative Decoding NAACL 2025
Graph-Structured Speculative Decoding ACL 2024
How Speculative Can Speculative Decoding Be? COLING 2024
Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration NIPS 2024
Towards Fast Multilingual LLM Inference: Speculative Decoding and Specialized Drafters EMNLP 2024
Context-Aware Assistant Selection for Improved Inference Acceleration with Large Language Models EMNLP 2024
Cascade Speculative Drafting for Even Faster LLM Inference NIPS 2024