Flopper
GPU specs and live rental prices from 24 clouds, side by side
Emerged finds new products worth a look, daily — what’s new today
ai-infra-book
An open textbook that sizes LLM inference and training from first principles
If you are budgeting GPUs for inference or training, this book shows the arithmetic behind memory, throughput and cost instead of asking you to trust vendor numbers.
Bojie Li's open book on AI infrastructure works through LLM systems quantitatively: how much GPU memory one generation needs, how to optimise inference, how distributed training and serving are laid out, and where edge and cloud split the work. Twelve chapters are readable on the web or as an auto-built PDF, with calculators, experiments and diagram scripts in the repo. It is written in Chinese and still a revised first draft.
More like this
Warp
Run trillion-parameter models on a laptop by streaming weights from NVMe
Goethe
Turn a Linux box with NVIDIA GPUs into a private, OpenAI-compatible endpoint
Sunk Cost
How long until a local LLM machine pays for itself against API bills
Edge0
Run large mixture-of-experts models on a Mac by streaming experts from SSD
Jinfer
An AI inference engine that runs inside the JVM, with no Python sidecar