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
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| compressed-trunk.md 2.2 KB | ||
| huf_encode.py.shelved 5.3 KB | ||
| int8-draft-container.md 6.5 KB | ||
| k3_huf.h.shelved 6.4 KB | ||