DFlash: Block Diffusion for Flash Speculative Decoding
Paper
• 2602.06036 • Published
• 42
DFlash
Block Diffusion for Flash Speculative Decoding
-
-
z-lab/Qwen3.5-4B-DFlash
Text Generation • 1B • Updated • 92 -
z-lab/Qwen3.5-9B-DFlash
Text Generation • 3B • Updated • 191 • 2 -
z-lab/Qwen3.5-35B-A3B-DFlash
Text Generation • 1B • Updated • 425 • 3 -
z-lab/gpt-oss-20b-DFlash
Text Generation • 0.8B • Updated • 792 • 10 -
z-lab/gpt-oss-120b-DFlash
Text Generation • 0.8B • Updated • 36 -
z-lab/Qwen3-4B-DFlash-b16
Text Generation • 0.5B • Updated • 27k • 22 -
z-lab/Qwen3-8B-DFlash-b16
Text Generation • 1B • Updated • 7.53k • 20 -
z-lab/Qwen3-Coder-30B-A3B-DFlash
Text Generation • 0.5B • Updated • 1.07k • 27 -
z-lab/LLaMA3.1-8B-Instruct-DFlash-UltraChat
Text Generation • 1B • Updated • 1.59k • 2