SGLang v0.5.20 ships: Intel XPU support, up to 52% faster decode
hsu_byron · x · 2026-09-23
SGLang v0.5.20 is out, welcoming Intel XPU to standard releases. Highlights:
- RL sampling masks make rollouts more reliable, with up to 52% faster decode
- Unified Radix Tree adds SWA branching-point caching: 20pt higher cache hit rate, 1/3 lower TTFT
- DSpark now supports PD + DCP for long-context serving
- SGLang Simulator brings scheduler & cache experiments to CPU
- ROCm model loading up to 12.5× faster
- SGLang-Diffusion cuts E2E latency up to 38%
New models include GLM-5.3-Flash, Qwen3.8-Flash-Next, K2 Horizon, Hy4-Preview, FastH3, and VDN-H3.
More from Infra
- Gas-for-AI-datacenters forum co-located with CoRL shows energy demand spillover — carlosdponx · 2026-11-12
- a16z podcast: Mike Volpi on Cisco's 70+ acquisition playbook and the AI buildout — a16z · 2026-11-12
- AMD to pass Intel in server revenue by mid-2027 as share gains 6 points a year — BenBajarin · 2026-11-12
- Study: Reflective Data Center Roofs Actually Cool Daytime Ground by 1.8-2.2°C — SumitGup · 2026-11-12
- Tsinghua's BaGuaLu-2 tames MoE expert-load spikes at runtime, accepted to SC26 — jiqizhixin · 2026-11-12
- antirez backs low-bit DeepSeek 4.1 Flash over Qwen 27B dense on Apple M5 Macs — antirez · 2026-11-12