and here's a slightly less-zoomed backward pass. autograd is running, backward is happing, etc. etc. seems all fine and good to me
AI
-

GPU utilization troubleshooting: why only 30% despite full memory
By
–
yet here's proof that my GPU utilization is still trash. if forward or backward is ~always happening according to the profiler, and memory is decently full now (at least over 50%)… …then how is my GPU being used only on average 30% of the time? what am i missing here?! help
-

PyTorch GPU Utilization Issues: Profiling Forward Backward Pass
By
–
alright y'all. still having GPU utilization issues and against my better judgement i broke out the PyTorch profiler. posting a few screenshots. doesn't seem like I/O is an issue (no gaps) how is GPU util so bad (~30%) if either forward or backward is running almost always?
-

Inside BERT: Forward Pass Architecture and Operations
By
–
here's a zoomed in forward pass. it's classic BERT stuff. linear layers, matmuls, softmaxes, some other stuff
-
Robotics and AI as the only solution to problems
By
–
100% agree. There is no other way than robotics and ai to solve the problems
-

Fine-tune SDXL Image Generator with Just 5 Images
By
–
We made it super easy to train your own image generator! You can finetune SDXL on any subject, scene, or style you want, with as few as 5 images. Run it on an API with Replicate as soon as it's finished training. Literally couldn't be easier
-

ChatGPT and DALLE comics top reader feedback in newsletter
By
–
ChatGPT + DALLE creating comics in each edition of the AI Breakfast newsletter started as an experiment 2 months ago, and now generates more reader feedback than anything I write about. Took a lot of prompt massaging to get the system down, but I like where it’s ended up.
-
Using Metadata for AI-Generated Image Identification
By
–
I would bet on “Labelling ai generated images” based on the metadata
