Tag archive
Got Qwen3.8-Flash-Next 125B MoE hitting 97 tok/s on a single Colab A100-80GB. Here's my full setup for an OpenAI-compatible endpoint.
Turning a free Colab T4 + Easy-Wav2Lip into a real production line: 9 videos in 491s, nohup batching, and the 5 traps that cost a session each.
Originally published at norvik.tech Introduction Explore the intricacies of fine-tuning...
While some of my recent posts have involved using the Colab extension for VS Code and the...
Adding UI to Colab You can show UI in a Google Colaboratory notebook. Input forms,...
My “Rav Oury Cherki RAG pipeline” project is all about making his teachings accessible. This past...
If you have ever tried to create a multi-panel collage by stitching many images together you have...
New York City's Office of Technology Innovation provides a collection of useful APIs that let you...
下午在 Colab 被一個奇妙的問題卡了好久，我把問題簡化成底下這個儲存格： from IPython.display import Markdown m =...
Last week we had a dlt (Data Load Tool) workshop in Data Engineering class. I'll talk about dlt in...
Idea This simulation about thermodynamics. Basic boiling of water, I was interested in...