Back
Similar todos
getting into some CUDA hell 
#spectropic
try save money by reducing steps of upscaler from 18 to 9 and image gen from 40 to 30 without noticeable differences so then we save 1 minute of GPU time per image gen or $0.07 per photo or tens of thousands $ per month 
#photoai
research cpu gpu performance bottlenecks on xen passthru #optimizing
Improve generating 
#lyricallabs
Ordered two Nvidia GPUs to implement some ✨ magic into 
#2markdown.
Improved utilization of the 
#screenshotone GPU server by using Vulkan API with NVIDIA GPUs. It has improved rendering performance by 1000% in some cases.
Simplify code and reduce build time by 2 minutes 
#composeexamples
achieve nice speedup 
#consulting
