gitpulse

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.

12,252 星标1,891 复刻CApache-2.0推送于 2026-11-16

在 GitHub 上查看 →

星标动能

今日+68 (+0.6%)
本周+703 (+6.1%)
本月+3,157 (+34.7%)

主题

avx2c99cpu-inferencedeep-learningfrom-scratchinference-enginekimi-k3linear-attentionllmllm-inferencemachine-learningmemory-efficientmixture-of-expertsmoemxfp4quantizationsimdsystems-programmingtransformerzero-dependencies