Back
Similar todos
Load previous page…
benchmarking NVIDIA A16 vs A40 vs A100 GPUs economics to scale 
#crisp mirage
optimize function further to 0.17 seconds. went from 4s -> 1.68s -> 0.17s 
#pe
reduced 
#killspam processing time by 40%
look at more cuda errors
finish migrating 
#mirage kubernetes intel and nvidia gpu instances to scaleway, getting last-generation NVIDIA L40S + L4 GPUs, running much smoother now! (previously: old A40 and A16)
Made great progress in rewriting the function that creates the data structure used to construct the timing graph. 
#rhymecraft
Success with reducing API call time from ~6 seconds to ~2 seconds 
#fashn
Get cuda errors 
#spectropic
Push some caching improvements to 
#postcard
