SGLang v0.5.18 lands major model and perf updates

Tools official 1 src. ~1 min

SGLang v0.5.18 shipped on 2026-08-22 with 710 PRs from 212 contributors, adding Muse Glimmer, Intern-S2-Mobius, SANA-Video, LingBot-Video-MoE, LTX-2.5, Cosmos3 Edge & Distilled, and LongCat-Image. Overlapped checkpoint staging makes Qwen3-32B on H100 start 2.38x faster (35.6s vs 84.8s) under --startup-weight-load-mode overlap; TP LMHead All-to-All cuts DeepSeek-V4-Pro B200 decode LMHead time from 320µs to 169µs; FlashInfer MNNVL gives DeepSeek-V4-Flash TP4 decode up to +6.9% at small batches.

Why it matters

Large monthly SGLang cut adds video/multimodal diffusion models and Blackwell perf wins

Importance: 2/5

Standard release

sglang inference serving release

Sources

official Releases · sgl-project/sglang