WhiFlash-Neural Cross-paradigm speculative decoding method to accelerate LLM inference (Kwon et al., Findings of EMNLP 2026). WhiFlash/Qwen3-8B-NeuralRouter-df-e3 Updated 13 days ago • 323 WhiFlash/Qwen3-8B-NeuralRouter-ddt-e3-b32 Updated 13 days ago • 313 WhiFlash/Qwen3-8B-NeuralRouter-ddt-e3-b128 Updated 13 days ago • 310 WhiFlash/Qwen3-4B-NeuralRouter-df-e3 Updated 13 days ago • 165
SpecVocab EAGLE-3 draft models trained for SpecVocab (Williams et al., Findings of ACL 2026). WhiFlash/Qwen3-8B-EAGLE3 0.4B • Updated 16 days ago • 2.75k WhiFlash/Qwen3-4B-EAGLE3 0.2B • Updated 16 days ago • 1.74k Speculative Decoding with a Speculative Vocabulary Paper • 2602.13836 • Published Jul 17 • 1
WhiFlash-Neural Cross-paradigm speculative decoding method to accelerate LLM inference (Kwon et al., Findings of EMNLP 2026). WhiFlash/Qwen3-8B-NeuralRouter-df-e3 Updated 13 days ago • 323 WhiFlash/Qwen3-8B-NeuralRouter-ddt-e3-b32 Updated 13 days ago • 313 WhiFlash/Qwen3-8B-NeuralRouter-ddt-e3-b128 Updated 13 days ago • 310 WhiFlash/Qwen3-4B-NeuralRouter-df-e3 Updated 13 days ago • 165
SpecVocab EAGLE-3 draft models trained for SpecVocab (Williams et al., Findings of ACL 2026). WhiFlash/Qwen3-8B-EAGLE3 0.4B • Updated 16 days ago • 2.75k WhiFlash/Qwen3-4B-EAGLE3 0.2B • Updated 16 days ago • 1.74k Speculative Decoding with a Speculative Vocabulary Paper • 2602.13836 • Published Jul 17 • 1
