context7.json

{
  "$schema": "https://context7.com/schema/context7.json",
  "url": "https://context7.com/1bit-monster/engine",
  "public_key": "pk_woGfNaBfmOKTjJDCp8JpR",
  "projectTitle": "1bit engine",
  "description": "C++ inference engine behind an OpenAI-compatible API, running inside Lemonade on AMD Ryzen AI: the XDNA 2 NPU, HRX with HIP kernels on the iGPU.",
  "folders": [
    "docs"
  ],
  "excludeFolders": [
    "third_party",
    "tools",
    "tests",
    "patches"
  ],
  "excludeFiles": [
    "LICENSE",
    "NOTICE"
  ],
  "rules": [
    "Serve models with `1bit serve`; it exposes an OpenAI-compatible API and runs as Lemonade's `onebit` backend.",
    "Pick the device with `--device` (auto, npu, hrx, cpu, ds4, onnx); an NPU model directory runs on the NPU fast lane, and `auto` runs plain GGUF files on HRX. On the GPU the engine is pure HRX with HIP kernels (no Vulkan, ROCm backend, Metal, ZINC or CUDA): Lemonade's own backends serve those.",
    "Prefer Unsloth Dynamic GGUFs: UD-Q4_K_XL is the lean default, UD-Q5_K_XL the accurate choice.",
    "For one user at a time use `--mtp`; for many simultaneous requests use `--parallel`.",
    "Documentation lives at https://1bit.gg; measured results are on the GitHub wiki."
  ]
}