SGLang Q4 roadmap: 10+ accelerator families supported, plugin system makes new backends first-class
ying11231 · x · 2026-11-12
SGLang published its Q4 2026 multi-hardware roadmap: the inference engine now runs on 10+ accelerator families, with out-of-tree plugin backends as a first-class path.
- In-tree Q4 focus: NVIDIA roadmap refresh; AMD MI45x/Helios/Ryzen AI with megakernels, speculative decoding, HiCache, RL; Google TPU day-0 frontier models and RL rollout; Ascend NPU; Intel Xeon CPU/XPU; T-Head PPU and Cambricon MLU
- New plugin backends: AWS Trainium and MetaX
- Platform work: capability-based device gating, plugin-honored speculative decoding/quantization, production serving audit across all backends
More from Infra
- Gary Marcus amplifies warning to price in end of Jensen Huang's circular-financing demand engine — GaryMarcus · 2026-11-12
- Hippius Hub Positions Itself as Decentralized Hugging Face with One-Line Import Swap — const_reborn · 2026-11-12
- Who could replace Jensen Huang? TechCrunch drafts a shortlist of possible Nvidia successors — TechCrunch AI · 2026-11-12
- SGLang ships Unified Memory: one shared arena kills KV partition waste in hybrid models — BanghuaZ · 2026-11-12
- Cerebras explains wafer-scale yield: independent voltage tuning across 84 die regions plus redundant cores — Sethwinterroth · 2026-11-12
- gVisor joins CNCF with Modal as maintainer, running 40M+ containers daily — charles_irl · 2026-11-12