This weekend, I probably built the most ambitious project I have ever worked on. It is a full graph compiler for vision pipelines, against cuda, metal, cpu, remote models, with load shedding, batching, time freshness invariants, NATS streaming, including a full UI design system, with ofc an extensive monitoring setup (down to individual GPU lanes), from zero in 2 days, and it just works, I can point 20 clients at it, streaming 50+ video feeds for 24h now, with the most ridiculous model graphs, javascript runtime callbacks that feedback into further CUDA inference. I can't share more here but it is absolutely mental.I used the opportunity to distill the codebase into a series of textbooks for me to learn about dataflow punctuations, handling multiple clocks (there's about 8 time domains in the system: incoming video, proxied video, vision system frame input, model computation clock, guaranteed result time, prospective result time (when we will have collected all the computations for the...
Related
Don’t pull out too early, stay hard when things get difficult. 🗣🗣🗣#Nvidia #AI #LessonLearned
Don’t pull out too early, stay hard when things get difficult. 🗣🗣🗣#Nvidia #AI #LessonLearned
Many people are obsessing over the "discovery" that if you ask an AI to "pick a random number" it will most likely choos...
Many people are obsessing over the "discovery" that if you ask an AI to "pick a random number" it will most likely choose "7". Folks, this is meaningless trivia. Large Language Mod...
Jenny Lee and Tanaya Macheel report on the shocking news that Nvidia turmoil is shaking futures! Nasdaq-100 futures slid...
Jenny Lee and Tanaya Macheel report on the shocking news that Nvidia turmoil is shaking futures! Nasdaq-100 futures slid 0.8% after reports emerged of a potential CEO Jensen Huang ...