Back
Similar todos
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)
fix broken nvidia a100 gpu server at vultr which has put 
#crisp mirage down for whole night due to being out-of-stock and no replacement physical node could be allocated
get annoyed at complication of GPU costs across providers so make a spreadsheet to try to rank top ~10 places to run GPU in price 
#mused docs.google.com/spreadsheets/…
deploy x10 performance improvement on #crisp mirage translation model
spend 1h debugging some k8s complexity-induced issue after a node failure at cloud provider for #crisp mirage gpus
make Nvidia stock proxy checker by testing how many GPUs available on Lambda 
#life nomadlist.com/lambda_gpu_avai…
research cpu gpu performance bottlenecks on xen passthru #optimizing
pay $1000 for more GPU credits 
#interiorai
provision batch of L4 and L40S GPUs at Scaleway for #mirage since our account got validated and quotas lifted
finish some #crisp chatbot ai inference code going to mirage api which manages all our gpus
implement #crisp mirage dashboard
migrate #crisp livetranslate to the mirage translation model, running on our own gpus
Ordered two Nvidia GPUs to implement some ✨ magic into 
#2markdown.
