Blog
Releases, benchmarks, and deep dives from the SGLang team.
September 23, 2026
Unified Radix Cache in SGLang: one tree for hybrid model prefix caching
SGLang TeamSGLang Deep Dive
September 20, 2026
RLinf x SGLang: Integrating Cosmos3 from Fine-Tuning to Efficient Parallel Evaluation
RLinf Team & SGLang TeamSGLang Deep Dive
September 10, 2026
DeepSeek-V4.1 Flash on SGLang: from 35 to 873 tokens/s
SGLang TeamSGLang Deep Dive
September 9, 2026
SGLang and Miles Add Day-0 Support for DeepSeek-V4.1
SGLang & Miles TeamDay-0 Support
August 27, 2026
Breakable CUDA Graph in SGLang: 5× faster graph builds, 1.93× faster prefill
SGLang Team & Meta TeamSGLang Deep Dive
August 19, 2026
Kimi K3: Architecture and SGLang Day-0 Support
SGLang Team & Moonshot AI TeamDay-0 SupportSGLang Deep Dive