SGLang Adds MoE Support
BanghuaZ · x · 2026-07-13
A community project update for SGLang: it now includes MoE support.
- Key capabilities include:
- Configurable offloading
- SM120 kernels
- MoE compatibility for SGLang
- The report mentions this solution supports running 2.7bpw in vram, balancing speed and quality recovery via offloading.
- The author notes it was inspired by vllm-moet and looks incredibly fast based on benchmark performance.
Related event: SGLang Community Project Adds MoE Support(2 posts)→
More from Infra
- PyTorch details 2.12x faster on-device streaming ASR on Arm SME2 via ExecuTorch — PyTorch · 2026-10-27
- Revenue per GPU can rise as token prices fall, argues Gavin Baker — GavinSBaker · 2026-10-27
- Anthropic S-1: only $19B total compute spend since inception, overbuild warning — bookwormengr · 2026-10-27
- CoreWeave, You.com and NVIDIA lift BrowseComp 22.9% in 3-week RL post-training sprint — RichardSocher · 2026-10-27
- Grid queues make power architecture an AI-factory decision; Exowatt and Redwood offer fixes — ingliguori · 2026-10-27
- Two CVSS 9.9 Wasmtime flaws allow sandbox escape, one ARM64-only since 2020 — basedjensen · 2026-10-27