This sub has had a distinct lack of dancing 1girls lately

So many posts with actual new model releases and technical progression, why can’t we go back to the good old times where people just posted random waifus? /s Just uses the standard Wan 2.2 I2V workflow with a wildcard prompt like the following repeated 4 or 5 times: {hand pops|moving her body and shaking her …

ML 19569 1

TII Falcon-H1 models now available on Amazon Bedrock Marketplace and Amazon SageMaker JumpStart

This post was co-authored with Jingwei Zuo from TII. We are excited to announce the availability of the Technology Innovation Institute (TII)’s Falcon-H1 models on Amazon Bedrock Marketplace and Amazon SageMaker JumpStart. With this launch, developers and data scientists can now use six instruction-tuned Falcon-H1 models (0.5B, 1.5B, 1.5B-Deep, 3B, 7B, and 34B) on AWS, and have access …

1 xN8hT4Emax 1000x1000 1

Scaling high-performance inference cost-effectively

At Google Cloud Next 2025, we announced new inference capabilities with GKE Inference Gateway, including support for vLLM on TPUs, Ironwood TPUs, and Anywhere Cache.  Our inference solution is based on AI Hypercomputer, a system built on our experience running models like Gemini and Veo 3, which serve over 980 trillion tokens a month to …