ferrum-kernels 0.7.6

Unified compute kernels (CUDA/Metal/CPU) and model runner for Ferrum inference
Documentation

ferrum-kernels

There is very little structured metadata to build this page from currently. You should check the main library docs, readme, or Cargo.toml in case the author documented the features in them.

This version has 9 feature flags, 0 of them enabled by default.

default

This feature flag does not enable additional features.

cuda

fa2-source

marlin

This feature flag does not enable additional features.

metal

tensor-parallel

triton-kernels

vllm-marlin

vllm-moe-marlin

vllm-paged-attn-v2