Summary
SGLang 0.5.22 introduces an InstantTensor loader that maintainers say makes models load up to ten times faster, adds new model and diffusion support, and improves DeepSeek-V4.1 throughput on H200 GPUs. It also fixes a bug that could resume hybrid-linear models from incorrect Mamba states when speculative decoding and structured output were combined.
Why it matters
Serving efficiency and silent-correctness failures directly affect the cost and trustworthiness of production inference, especially for large open-weight models.