Rethinking Research Notes: Adopting Zettelkasten for My Paper Explanations
Announcing the adoption of the Zettelkasten method for structuring paper explanations on abhik.xyz/papers to improve connections and reduce redundancy
Deep dive into machine learning, computer vision, and software engineering. Expert insights on AI, local LLMs, quantization, and practical implementation details from real-world projects.
Announcing the adoption of the Zettelkasten method for structuring paper explanations on abhik.xyz/papers to improve connections and reduce redundancy
Explore how torch.compile accelerates PyTorch models through kernel optimization. This article visualizes PyTorch kernel structures and their file mappings.
Learn why PyTorch throws the "view size is not compatible" error, understand tensor memory layout, and discover optimal solutions with performance benchmarks.
A detailed visualization of the file structure of GGML files, including the mapping of blocks to their corresponding positions in the file.
Dive deep into Kernel Fusion, a technique that combines multiple neural network operations into unified kernels improving performance in deep learning models.
YOLOv5 Simplified: A Beginner's Visual Guide to Understanding Each Step of the YOLOv5 Model Architecture where we will be visualizing the YOLOv5 model architecture and its components.
How OpenMMLab projects use the Registry Pattern to dynamically load models
Explore the fascinating concept of magic numbers in computing and discover how 4A464946 serves as the unique identifier for JPEG files.
A detailed exploration of image encoding, covering the fundamental concepts, differences between lossy (like JPEG) and lossless (like PNG) compression techniques, and their underlying mechanisms.
LLMs and Text Encoding