rlx 0.2.13

RLX — small ML compiler + runtime for transformer inference and training. JAX-shaped IR, autodiff, vmap, on top of CPU / Apple Silicon (Metal / MLX) / NVIDIA / AMD / TPU / wgpu backends. This is the prelude crate; pulls in rlx-ir / rlx-opt / rlx-runtime and re-exports the common types.
Documentation

rlx

There is currently very little information to present on this page because Docs.rs has only limited support for extracting structured feature metadata from Cargo crates. This issue is tracked in Rust RFC #3416. Check this library's main docs, readme, and Cargo.toml in case its authors have documentation for features available there instead.

This version has 31 feature flags, 2 of them enabled by default.

default

cpu (default)

tensor (default)

all-cpu

apple-silicon

bench

blas-accelerate

blas-mkl

blas-openblas

coreml

cortexm

cuda

distributed

edge

fpga

gguf

gguf-convert

gpu

linalg

metal

mlx

mlx-cuda

nvidia

oneapi

onnx

optim

rocm

sparse

splat

This feature flag does not enable additional features.

tpu

umap

vulkan