SSealbook

FareedKhan-dev/kimi-k3-in-c

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.

avx2c99cpu-inferencedeep-learningfrom-scratchinference-enginekimi-k3linear-attentionllmllm-inference

License & maintenance

Apache-2.0 is a permissive license: free to use commercially with attribution.

Last code push 16 days ago.