VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention Paper • 2609.15810 • Published 14 days ago • 51
VC-Attention: Value Smoothing and Softmax Casting for Low-bit Attention Paper • 2609.15810 • Published 14 days ago • 51
FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution Paper • 2608.16157 • Published Aug 17 • 112
Quant VideoGen: Auto-Regressive Long Video Generation via 2-Bit KV-Cache Quantization Paper • 2602.02958 • Published Feb 3 • 35