FareedKhan-dev/kimi-k3-in-cC10.1k
GitHubで見る →
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.
技術情報
言語
C
ライセンス
Apache-2.0
最終更新
2026-10-02
スター数
10,103
フォーク数
1,614
Issue数
6
トピック
avx2c99cpu-inferencedeep-learningfrom-scratchinference-enginekimi-k3linear-attentionllmllm-inferencemachine-learningmemory-efficientmixture-of-expertsmoemxfp4quantizationsimdsystems-programmingtransformerzero-dependencies
関連リポジトリ
huggingface/transformers
huggingface/transformersPython167.1k
rasbt/LLMs-from-scratch
rasbt/LLMs-from-scratchJupyter Notebook94.2k
rohitg00/ai-engineering-from-scratch
rohitg00/ai-engineering-from-scratchPython61.0k
vllm-project/vllm
vllm-project/vllmPython94.7k
higgsfield-ai/higgsfield
higgsfield-ai/higgsfieldJupyter Notebook5.2k