Ben Chuanlong Du's Blog

It is never too late to learn.

Scaling Law for LLM

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

Beyond neural scaling laws – Paper Explained

Scaling Laws refer to the observed trend of some machine learning architectures (notably transformers) to scale their performance on predictable power law when given more …

Tips on ONNX

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

ONNX Runtime

ONNX Runtime is a cross-platform inference and training machine-learning accelerator. ONNX Runtime inference can enable faster customer experiences and lower costs, supporting models from deep learning frameworks such as …

JIT and Domain Specific Compilers

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

numba

Hummingbird

Hummingbird compiles trained ML models into tensor computation for faster inference.

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

XLA

deep learning …

Rust for Machine Learning

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

candle

Candle is a minimalist ML framework for Rust with a focus on easiness of use and on performance (including GPU support).

dfdx

dfdx is an ergonomics & safety focused deep learning …

Hardware for AI

Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!

TVM for deep learning is kind of like LLVM for programming languages.

Nvidia TensorRT

Embedded/Edge AI

Jetson Nano

Google Coral

Intel Neural Compute Stick 2

https://heartbeat.fritz.ai/edge-tpu-google-coral-usb-accelerator-cf0d79c7ec56 …