GitHub - AutoMQ/automq: A cloud native implementation for Apache Kafka, reducing your cloud infrastructure bill by up to 90%.
A new embedding model cuts vector DB costs by ~200x.
It also outperforms OpenAI and Cohere models.
Here's a complete breakdown (with visuals):
Avi Chawlax.com

this is probably the most cost-effective large training run ever done. with one simple trick, Nvidia was able to decrease their $/GPU expenditures by up to 90% https://t.co/xaUDJelGcr