SGLang Ships Day-0 Kimi K3.1 Support With Out-of-the-Box Megakernel
BanghuaZ · x · 2026-11-06
SemiAnalysis congratulates the SGLang team (sglproject / RadixArk) on Day-0 support for Kimi K3.1:
- Day-0 performance: SGLang serves Kimi K3.1 efficiently from launch day
- Megakernel support ships out-of-the-box
- The attached chart compares Kimi K3.1 Pro agentic tokens per $1 TCO vs P90 interactivity across GB200/GB300 NV72 (Dynamo SGLang), B200/B300, and MI355X configurations
Day-0 inference support is becoming a key competitive metric for serving stacks as new open models launch.
More from Infra
- Vivek Wadhwa: Big Tech's trillion-dollar bet on data centers is a mistake — sanjaykalra · 2026-11-06
- Is AMD 7900 XT/XTX viable for video generation in late 2026? — Beneficial_Fish_7509 · 2026-11-06
- Blue Origin unveils Northstar engine: 715,000 lbf thrust, 30% lighter than BE-4 — beffjezos · 2026-11-06
- DFlash drafts whole token blocks in parallel to fix speculative decoding bottleneck — Lianhuiq · 2026-11-06
- A single desktop B70 runs an entire AI livestream radio, generating music in real time — prince_pringle · 2026-11-06
- Inferact, founded by vLLM creators, now serves 7 trillion tokens a day — Xianbao_QIAN · 2026-11-06