Woon Yee Ng

Papers that credit Woon Yee Ng in their source bylines. Matching names may refer to different researchers.

1 results

1. PaperSearch & Data

   FP4 cache decoding keeps accuracy close while raising serving capacity

   BitDecoding-FP4 pairs four-bit cache storage with GPU kernels, keeping Qwen3 accuracy close to BF16 across seven tested tasks.

   Added to Chiosa Nov 09, 2026