Writing
- What continuous batching changes: reading three LLM inference traces
- Where does LLM inference time go? Prefill, decode, and KV cache on Apple silicon
- Compressing a ResNet for the edge: a cat breed + head-box detector
- Neural network quantization — from k-means codebooks to integer-only inference
- Neural network pruning — from fine-grained to channel pruning and everything in between
- CNN from 0 — why convolutional networks exist and what every layer actually does
- 96% full-board accuracy on chess recognition — what the papers say and what actually worked
- Pipe vs shared memory: what actually happens when you pass a tensor between processes