Block Diffusion for Flash Speculative Decoding
AI & ML interests
Efficient AI
Recent Activity
Papers
DFlash: Block Diffusion for Flash Speculative Decoding
ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
-
ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
Paper • 2511.10645 • Published • 8 -
z-lab/Qwen3.5-27B-PARO
Image-Text-to-Text • 6B • Updated • 1.61k • 10 -
z-lab/Qwen3.5-9B-PARO
Image-Text-to-Text • 3B • Updated • 51.2k • 41 -
z-lab/Qwen3.5-4B-PARO
Image-Text-to-Text • 1B • Updated • 15.4k • 13
Block Diffusion for Flash Speculative Decoding
Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
-
ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference
Paper • 2511.10645 • Published • 8 -
z-lab/Qwen3.5-27B-PARO
Image-Text-to-Text • 6B • Updated • 1.61k • 10 -
z-lab/Qwen3.5-9B-PARO
Image-Text-to-Text • 3B • Updated • 51.2k • 41 -
z-lab/Qwen3.5-4B-PARO
Image-Text-to-Text • 1B • Updated • 15.4k • 13
models 29
z-lab/Qwen3.5-27B-DFlash
Text Generation • 4B • Updated • 248 • 6
z-lab/Qwen3.5-0.8B-PARO
Image-Text-to-Text • 0.4B • Updated • 785 • 1
z-lab/Llama-2-7b-hf-PARO
Text Generation • 1B • Updated • 311 • 1
z-lab/DeepSeek-R1-Distill-Llama-8B-PARO
Text Generation • 1B • Updated • 531 • 1
z-lab/Qwen3.5-27B-PARO
Image-Text-to-Text • 6B • Updated • 1.61k • 10
z-lab/Qwen3.5-9B-PARO
Image-Text-to-Text • 3B • Updated • 51.2k • 41
z-lab/Qwen3.5-4B-PARO
Image-Text-to-Text • 1B • Updated • 15.4k • 13
z-lab/Qwen3.5-2B-PARO
Image-Text-to-Text • 1B • Updated • 365 • 2
z-lab/Qwen3-14B-PARO
Text Generation • 2B • Updated • 544 • 2
z-lab/Qwen3-8B-PARO
Text Generation • 1B • Updated • 618 • 1
datasets 6
z-lab/gsm8k-filtered
Viewer • Updated • 1.31k • 10
z-lab/mt-bench-filtered
Viewer • Updated • 79 • 12
z-lab/mbpp-sanitized-filtered
Preview • Updated • 13
z-lab/humaneval-filtered
Viewer • Updated • 137 • 14
z-lab/qwen3-4b-instruct-100k
Preview • Updated • 100k • 30
z-lab/qwen3-4b-thinking-100k
Viewer • Updated • 100k • 17