Forklifts require training(zacsweers.dev)

48 points by pandanomic 1 year ago | 22 comments

Python Dict – An Explorable Explanation(just-taking-a-ride.com)

40 points by akbarnama 3 years ago | 5 comments

Writing high-performance matrix multiplication kernels for Blackwell(docs.jax.dev)

58 points by lairv 1 year ago | 5 comments

TabPFN and TabICL vs. tuned XGBoost: the model that doesn't train won 14/14(efraingaray.com)

21 points by EfrainGaray 28 days ago | 9 comments

Blog post benchmarking TabPFN and TabICL foundation models against tuned XGBoost on fourteen tabular datasets, finding the no-training models won all fourteen.

MLX: NumPy like framework for Apple Silicon by Apple(ml-explore.github.io)

131 points by dagmx 2 years ago | 12 comments

JAX – NumPy on the CPU, GPU, and TPU(jax.readthedocs.io)

234 points by peter_d_sherman 3 years ago | 129 comments