TorchSpec open-sources 3 SOTA speculative decoding draft models for Kimi K3

hongyangzh · x · 2026-09-04

The TorchSpec team has released the Kimi K3 Draft Collection: three SOTA speculative decoding draft models (EAGLE-3, DFlash2, DSpark) trained with vLLM on NVIDIA GB200, with data recipes published. They also note a key empirical finding: high acceptance rate doesn't equal faster decoding — each draft architecture has its own drawbacks.

Related event: Kimi K3 gets open-sourced speculative decoding draft models(2 posts)→

Original post →

More from Infra

Infra channel →