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.
2717Curated repositories
65,483.7kTotal GitHub stars
Open sourceBuilt by the community
simd repositories
Hand-picked tools to improve your workflow.
Scala
Gluten is a middle layer responsible for offloading JVM-based SQL engines' execution to native engines.
High-efficiency floating-point neural network inference operators for mobile, server, and Web
C++
Performance-portable, length-agnostic SIMD with runtime dispatch