Local Model Quickstart One big point of feedback we've gotten is people want more documentation for how to use local models in chains As part of v0.1.0 we've updated our getting started to now highlight running OSS models! We also have a section on RAG with local models,
SOFTWARE
-
Nvidia Advances AI PC Technology with ACE Production Microservices
By
–
Nvidia makes the case for the AI PC at CES 2024 In addition to new RTX "Super" chip laptops, Nvidia announced that, building upon its ACE, for “avatar cloud engine,” it will offer “Production Microservices," which let game developers add to their games Nvidia programs for speech
-
API Key Usage Metrics Launch Announcement
By
–
Thanks for the shout-out and all these fantastic suggestions, Matthias! We’ve just rolled out API key usage metrics. It’s a start—keep the ideas coming!
-
New API key usage metrics now available
By
–
Great suggestion! We’ve taken a step in that direction with the new API key usage metrics, live as of Friday. Request logs are also on our radar as a popular request. Stay tuned for more!
-
Market Pullback in 2024: Tech Stock Profit Taking Begins
By
–
The TL Podcast for January 7th: A rough start It was a rough start to 2024 as investors seemed to take profits on a very strong 2023, especially as regards outperformers such as Apple and Nvidia, although there were several votes of confidence for semiconductors and software.
-
Volkswagen Integrates ChatGPT-Powered IDA Chatbot in Vehicles
By
–
I’m here at the @VW keynote at @CES where the company just announced it will integrate an automotive-grade chatbot powered by ChatGPT and other sources. Developed with Cerence Collaborate, features are voice activated for hands free use. #CES2024 The chatbot is named IDA. #CES
-
SAS Innovate 2026: Analytics, AI and Data ROI Solutions
By
–
We learned & connected last year— and let’s do it again April 16-19 at SAS Innovate Register to see what SAS customers and partners are doing to help you get the best ROI using SAS across data, analytics, AI & decisioning. http://
2.sas.com/6017Riec3 #SASInnovate #CloudAnalytics -
DeepCache compatibility with ControlNet Turbo and LCM
By
–
Is DeepCache compatible with ControlNet, Turbo, LCM?
-
DeepCache accelerates SDXL generation to 19 iterations per second
By
–
Faster vanilla SDXL with DeepCache in diffusers is interesting. @lucataco93 has got this up on Replicate: https://
replicate.com/lucataco/sdxl-
deepcache
… 1024×1024 at 25 steps seems to take ~3s on A100 (19it/s). More on DeepCache: https://
huggingface.co/papers/2312.00
858
…