storage is local + cloud inference for everything else. trying to figure out something scalable for that second part
SOFTWARE
-
Swift LPC Algorithm Open Source Release for On-Device Speech
By
–
We're releasing an open source Swift implementation of the LPC algorithm for on-device speech analysis. Uses Accelerate.framework and runs 2.75x faster than librosa on an M1 Pro! One of @hyperonline_
's first open source repos and a key part of our on-device pipeline for avatars: -
DeepFloydFilter Issue: Silent Processing and Motion Parameter Adjustment
By
–
…it was actually DeepFloydFilter silently eating everything; took me a while to notice there was a call in there. 27 does seem too low for motion, once the filter is off. Proposed fix, set DeepFloyd to verbose.
-
Creating HD Videos with SVD: Memory Optimization Techniques
By
–
If you've got the memory, you can make HD videos with SVD, using larger images.
— fofr (@fofrAI) 26 novembre 2023
This example is 1408 × 768 (bigger than 720p) straight out of SVD – no upscaling (but I did add interpolation).
Set the number of frames to decode at a time to 1 (decoding_t) to avoid OOM
1/2 pic.twitter.com/aeRXmlok5QIf you've got the memory, you can make HD videos with SVD, using larger images. This example is 1408 × 768 (bigger than 720p) straight out of SVD – no upscaling (but I did add interpolation). Set the number of frames to decode at a time to 1 (decoding_t) to avoid OOM 1/2
-
Databricks AI Predictive Optimization Enhances Data Performance
By
–
Databricks Predictive Optimization helps you optimize your table data layouts with #AI for improved performance and cost-efficiency. Discover how it can free up your time to focus on getting business value from your data. Now in public preview https://
bit.ly/3sg8tGz -
AI Search Tool Trade-offs: Speed vs Navigation Latency
By
–
Thanks! Caveat: you will be annoyed for navigational queries. The latency of Google’s index and page load teams is incredible. But, if that’s a bullet you’re okay biting, you’ll a great time on actually getting your answers. Your cumulative browsing time will be lower.
-
OpenRouter Integration Option Under Consideration
By
–
not yet. thinking about openrouter, or at least an option for it
-
Pair Programming as a Quiet Collaborative Development Practice
By
–
My experience of pair programming is that it's a fairly quiet activity.
-
Build RAG with Mistral-7B and LangChain Locally
By
–
Build your own RAG with Mistral-7B and LangChain Using local models can enable chatbots over your data while ensuring your data never leaves your computer Great for enterprise or privacy centric use cases This blog post by Madhav Thaker is one of the best resources we've