view post Post 194 Nanbeige4.3-33B DFlash2 speculative drafter ⚡️1.76× faster decoding on BF16, 1.65× on FP8, 1.51× on NVFP4. Agentic coding ~2.6×. Same outputs: exact rejection sampling. This is an early result, an improved version with higher acceptance is in training. SGLang 0.5.21, drop-in: ProCreations/Nanbeige4.3-33B-DFlash2 See translation 2 replies · 🚀 1 1 🔥 1 1 + Reply