Kimi K3 serving stack reaches 423 tok/s after DSpark draft-model tuning
ying11231 · x · 2026-07-28
Radixark says they trained a DSpark speculator draft model for Kimi K3 with SpecForge, raising batch-1 decode throughput from about 113 tok/s to 423 tok/s.
Reported gains
- +68% throughput at bs=256 on chat vs. verify-all, lossless
- Accept length of 5.67 on GSM8K and 5.36 on HumanEval
The quoted SGLang update says K3’s fast serving comes from native implementation and optimization of the new architecture, including fused KDA decode kernels, DP attention, DSpark, PD disagg, and KDA-aware prefix caching. It also says the stack has passed Kimi Vendor Verifier and is ready for production.
Related event: SGLang Day-0 Support for Kimi K3 Boosts Throughput to 423 tok/s(8 posts)→
More from Infra
- RTX 5090 hits $7K as PC gaming community goes into 'denial' over AI boom — PAstynome · 2026-10-27
- Wan2GP lands on Pinokio: 1-click AI video on 6GB GPUs — cocktailpeanut · 2026-10-27
- Wan2GP AMD one-click installer lands on Pinokio, runs AI video on 6GB VRAM — cocktailpeanut · 2026-10-27
- AWS on agent prompt caching: explicit + implicit patterns to slash token costs — AWS ML Blog · 2026-10-27
- Thieves spoofing GPS steal $100M+ in data center cargo since June — Ars Technica AI · 2026-10-27
- Lam Research: weekly token usage up ~250x in 18 months — Beth_Kindig · 2026-10-27