A developer released TurboGPT, an MIT-licensed byte-level GPT trainer written in CUDA C++ that trains a 22KiB transformer in 13 seconds. The tool builds on Windows with Visual Studio 2022 C++ tools an…
Trainproof v0.18.0, a deterministic linter for machine learning training runs, catches training failures such as a cross-entropy ignore_index collision that silently deletes a target from the loss whi…
Nansense, a new interactive PyTorch debugger, allows developers to pause training, step batch-by-batch, and time-travel to different epochs while visualizing activations, gradients, weights, and optim…
Machine learning teams are adopting visual debugging tools to gain real-time visibility into model internals during training, addressing the common problem of silent failures like vanishing gradients …