SGLang v0.5.15 Released
ying11231 · x · 2026-07-15
The quoted post highlights the release of SGLang v0.5.15, focusing on optimizations for production-grade inference services.
This update includes:
- Production tuning for GLM-5.2 NVFP4, achieving 500+ tok/s/user on 8x B300 and 450 tok/s/user on 4x GB300 (bs=1)
- Plans to share run commands and full technical details in upcoming threads and blogs
- Added support for multiple new models: Hunyuan 3, HRM-Text, NVIDIA LocateAnything-3B, Baidu Unlimited-OCR, JoyEcho, Qwen3.6
- Other major updates: Breakable CUDA Graph default capture path, built-in web search (powered by Exa), decode context parallelism for MLA models, and FlashInfer all-to-all
Related event: SGLang v0.5.15 tunes GLM-5.2 serving to 500+ tok/s on 8×B300(6 posts)→
More from Infra
- Musk: robot RAM demand will dwarf everything else, and 100% of superintelligence compute goes to deep space — elonmusk · 2026-10-27
- 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
- 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