DFlash: Block Diffusion for Flash Speculative Decoding Paper • 2602.06036 • Published 16 days ago • 42
DFlash: Block Diffusion for Flash Speculative Decoding Paper • 2602.06036 • Published 16 days ago • 42
ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference Paper • 2511.10645 • Published Nov 13, 2025 • 6
ParoQuant: Pairwise Rotation Quantization for Efficient Reasoning LLM Inference Paper • 2511.10645 • Published Nov 13, 2025 • 6