DFlash 2 speeds up GLM-5.3-Flash by 2.8x via block-diffusion speculative decoding
Lianhuiq · x · 2026-08-28
Inco AI released the DFlash 2 draft model for GLM-5.3-Flash, achieving a 2.8x speedup using speculative decoding. DFlash 2 employs a block-diffusion mechanism to predict a whole block of tokens in one pass and track coherent paths with a lightweight selector. Benchmarks run on SGLang with NVIDIA GB300 GPUs show lossless decoding where greedy outputs match the target model exactly.
Related event: Inco AI Releases DFlash 2 Draft Model, Speeding Up GLM-5.3-Flash by 2.8x(3 posts)→
More from Infra
- Nvidia's developer base hits 11 million, up ~3.7x from 3 million in 2021 — Beth_Kindig · 2026-10-16
- Muse Spark Open runs locally on a Mac M3 Ultra via llama.cpp: frontier model on desktop — pcuenq · 2026-10-16
- Muse-Spark open-weights drop: 816B-A42B MoE model gets 359GB MLX 3-bit build — ns123abc · 2026-10-16
- Meta launches Muse Spark Open, says it runs on two M5 Ultra Mac Studios with Apple's help — The Verge AI · 2026-10-16
- vLLM ships Day-0 LoRA RL for Muse Spark Open, lifting AIME from 0.56 to 0.85 — vllm_project · 2026-10-16
- DSpark draft model for Muse Spark Open proposes 7 tokens per pass with 23-42% acceptance — vllm_project · 2026-10-16