Discover tools that make developers better.

FareedKhan-dev/kimi-k3-in-c

C · Trending

A 2.78-trillion-parameter Kimi K3 running inference on a single CPU in 8.24 GB of RAM. Portable C99: no BLAS, no framework, no GPU.

google/highway

C++

Performance-portable, length-agnostic SIMD with runtime dispatch

google/XNNPACK

C

High-efficiency floating-point neural network inference operators for mobile, server, and Web

apache/gluten

Scala

Gluten is a middle layer responsible for offloading JVM-based SQL engines' execution to native engines.