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.
- avx2
- c99
- cpu-inference
- deep-learning
47,133 repositories indexed
1–11 of 11 · Most stars
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.
Reliable PostgreSQL Backup & Restore
A simple, lightweight, flexible, embeddable, portable and multi-paradigm dynamic programming language for developing applications, tools, and domain-specific languages
One advanced and mature open-source MPP (Massively Parallel Processing) database. Open source alternative to Greenplum Database.
GRASS - free and open-source geospatial processing engine
:airplane: Multi-functional, compatible DIY general aviation proximity awareness system
Parallel solvers for sparse linear systems featuring multigrid methods.
libMesh github repository
An interactive parallel ssh client featuring autocomplete and asynchronous execution.
Legend of Elya — N64 game with a real 6.36M-parameter ternary transformer on the VR4300 MIPS III CPU. Zelda-style dungeon, AI NPCs, byte-level inference at 1.23 tok/s scalar / 2.19 tok/s on the RSP overlay (measured under ares, never on silicon). Built with libdragon.
Cross-platform, heap-free C test runner with parameterized and lifecycle-aware tests.