/explore
|
You are here 
|
github.com | ||
| | | | |
www.spheron.network
Qwen3.5-Omni handles text, audio, and video in one 30B MoE model (3B active per token). Here is the GPU sizing, vLLM setup, quantization options, and cost comparison for self-hosting it in production. |
|
| | | | | ||
| | | | |
michael-lewis.com
An introduction to vector search (aka semantic search), and Retrieval Augmented Generation (RAG). |
|
| | | | | ||
| | | | |
jonready.com
The hardware and software stack behind training and serving open-weights models from my home office. |
|
| | | | | ||
| | | | |
www.allthingsdistributed.com
Amazon Sagemaker enables data scientists and developers to quickly and easily build, train, and deploy ML models without getting mired in the challenges that slow this process down today. |
|
| | | |||
