SGLang launches zero-to-sglang course: build a mini-SGLang, ship your first PR
ying11231 · x · 2026-09-11
SGLang, together with Datawhale, is launching zero-to-sglang, a course taking learners from reading inference code to building a mini-SGLang and navigating the real codebase.
- Covers attention backends, CUDA Graphs, and prefill-decode disaggregation
- Designed to turn learning into a first high-quality open-source PR
- Aimed at onboarding more builders into the SGLang community
Related event: SGLang and Datawhale Launch Official zero-to-sglang Course(2 posts)→
More from Infra
- NVIDIA launches BioNeMo Inference Runtime public beta to speed up Boltz-2 and OpenFold2 — AllThingsApx · 2026-09-11
- Open-sourced inference acceleration for structure-based models ships benchmarked and documented — AllThingsApx · 2026-09-11
- NVIDIA's $89B quarterly data center revenue means compute is no longer an IT expense — PeterDiamandis · 2026-09-11
- NVIDIA scales financial clustering to 1M instruments across 64 GB200 GPUs — PyTorch · 2026-09-11
- OpenAI Agents API hits public beta; Cloudflare ships sandbox integration for cloud Codex agents — ritakozlov · 2026-09-11
- DeepSeek-V4.1-Flash lands on Fireworks: 552B MoE for coding and agents at 1/40th claimed cost — lqiao · 2026-09-11