Welcome 👋
This is the English section of Nebulamao’s Blog — notes and write-ups on AI engineering: LLMs, agents, RAG, model quantization/fine-tuning, and the bugs I hit along the way.
🌐 中文站点:https://blogs.xmccln.top
Posts
- Unlocking GPU-to-GPU P2P on the CMP 170HX — Nine Links in a Chain, and One Machine I Killed
- Putting a Gateway in Front of a Hundred ComfyUI Boxes: Two Days of Lessons
- MPK Single-Card Performance Root-Cause: Why It’s 3.4× Slower Than SGLang on the PPU-ZW810E
- Porting NVIDIA’s CUDA Megakernel (MPK) to China’s T-Head PPU-ZW810E
- Hi, I’m Nebulamao — A Developer Who Believes in the “Super Individual”