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
Builds are not enabled for this repository.
Workflows
files in.armgit/workflows/No workflow yet. Add a file such as .armgit/workflows/build.yml:
name: Build
on: [push, pull_request, manual]
jobs:
test:
image: node:22
steps:
- name: Install
run: npm ci
- name: Test
run: npm testNo builds yet.