Cross-paradigm speculative decoding method to accelerate LLM inference (Kwon et al., Findings of EMNLP 2026).
AI & ML interests
Cross-Paradigm Speculative Decoding
Recent Activity
View all activity
models 8
WhiFlash/Qwen3-4B-NeuralRouter-ddt-e3-b128
Updated • 185
WhiFlash/Qwen3-4B-NeuralRouter-ddt-e3-b32
Updated • 184
WhiFlash/Qwen3-4B-NeuralRouter-df-e3
Updated • 190
WhiFlash/Qwen3-8B-NeuralRouter-ddt-e3-b128
Updated • 336
WhiFlash/Qwen3-8B-NeuralRouter-ddt-e3-b32
Updated • 342
WhiFlash/Qwen3-8B-NeuralRouter-df-e3
Updated • 350
WhiFlash/Qwen3-8B-EAGLE3
0.4B • Updated • 2.83k
WhiFlash/Qwen3-4B-EAGLE3
0.2B • Updated • 1.8k
datasets 0
None public yet