50m ago · 6 min read · TL;DR A .cpu().numpy() call buried inside a forward pass was forcing a full CPU-GPU synchronization on every batch, every loop iteration. The GPU would finish its work in milliseconds, then sit idle
Join discussion
3d ago · 1 min read · This article analyzes the evolution of machine learning, which has evolved from a niche craft into the foundation of digital industry. The author points out that modern AI is not just algorithms but, above all, a complex MLOps infrastructure, encompa...
Join discussionMay 3 · 3 min read · Let's be honest: the current meta of AI development is just brute-forcing parameters until we run out of VRAM. It’s expensive, it’s inefficient, and it’s definitely not how a biological brain actually
Join discussionApr 28 · 3 min read · Introduction As the field of machine learning continues to blossom, the intricacies of neural network performance must be scrutinized more closely than ever. One phenomenon that has gained attention is gradient misalignment, which can severely affect...
Join discussion
Apr 28 · 3 min read · Introduction In the realm of artificial intelligence and machine learning, model complexity often correlates with performance. However, the balance between interpretability and efficiency can be a challenging one. Tridiagonal models, particularly whe...
Join discussionApr 26 · 5 min read · Built in the open. Trained in public. Shipped with the spirit of the open-source AI community. A February Evening That Changed My Thinking On 17 February, I walked into an Anthropic event carrying o
Join discussion
Apr 23 · 4 min read · When I first started learning PyTorch, one concept felt surprisingly confusing: The training loop — especially forward pass, loss, backpropagation, and optimizer steps. Over time, I realized somethi
Join discussion
Apr 18 · 28 min read · TLDR: A pretrained LLM is a generalist. Fine-tuning makes it a specialist. Supervised Fine-Tuning (SFT) teaches it your domain's language through labeled examples. LoRA does the same with 99% fewer trainable parameters. RLHF shapes its behavior using...
Join discussion
