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.
C avx2c99cpu-inferencedeep-learningfrom-scratchinference-enginekimi-k3linear-attentionllmllm-inferencemachine-learningmemory-efficientmixture-of-expertsmoemxfp4quantizationsimdsystems-programmingtransformerzero-dependencies
Insights
Commit activity
91 commits in the last 52 weeks (default branch, merge commits not counted).
Code frequency
+680,335 additions and −1,293 deletions in the last 52 weeks.
Contributors 10
Everyone who committed to the default branch.
| Contributor | Commits | Additions | Deletions |
|---|---|---|---|
Fareed Khan | 77 | +678,727 | −1,167 |
Douglas Mun | 3 | +196 | −13 |
Barba2k2 | 2 | +140 | −51 |
Coreywwj | 2 | +686 | −8 |
TROY665 | 2 | +184 | −23 |
Yongsheng Gao | 1 | +49 | −12 |
Shaalan Marwan | 1 | +9 | −9 |
leon costa | 1 | +16 | −7 |
auham | 1 | +326 | −1 |
dependabot[bot] | 1 | +2 | −2 |