GPU programming day 293: diving into SGLang via mini-sglang and MIT's EfficientML lecture 12
NandoDF · x · 2026-10-24
levidiamode's day-293 GPU programming log (retweeted by Nando de Freitas): after learning vLLM, they're studying SGLang using the mini-sglang repo (5,000-line compact implementation), plus Meta's kernel challenge and MIT Song Han's EfficientML.ai Lecture 12 covering KV cache optimizations, MoEs, MQA/GQA and RoPE — a useful path for learning LLM inference serving.
More from Infra
- Moonshot would need ~59K GB200s and $2.6B/yr just to match one DeepSeek cluster — teortaxesTex · 2026-10-24
- antirez makes the case for local AI as hacker's Samsung TV snooping saga hits HN — antirez · 2026-10-24
- PNG is slow because of deflate, not libpng — zlib-ng's SIMD wins — ssh4net · 2026-10-24
- Micron roadmap: HBM4 at 2.8 TB/s per stack, vertical HBM on GPUs by 2028 — rohanpaul_ai · 2026-10-24
- Hunyuan 3D 2.1 nearly unusable on Mac: errors above 512 resolution — idmimagineering · 2026-10-24
- China's Jiuzhang 4.0 claims 10^42-year speedup in 25 microseconds — but the task has no practical use — AryHHAry · 2026-10-24