skip to content
okami.mom / llama-cpp-bonsai

okami.mom/llama-cpp-bonsai

 fork

llama.cpp fork for Ternary Bonsai 2 27B: MTP speculation, suffix cache reuse (SCR), q8 KV, two-slot fairness, fused DeltaNet kernels

files main
  • .devops/ Aug 18
  • .gemini/ Dec 29, 2025
  • .github/ Sep 25
  • .pi/gg/ Aug 22
  • app/ Aug 12
  • benches/ Mar 16
  • ci/ Aug 23
  • cmake/ Aug 20
  • common/ Oct 14
  • conversion/ Sep 25
  • docs/ Sep 25
  • examples/ Sep 16
    • batched/ Apr 17
    • batched.swift/ Aug 21, 2025
    • convert-llama2c-to-ggml/ Aug 15
    • debug/ Apr 27
    • deprecation-warning/ Mar 4
    • diffusion/ Jul 23
    • embedding/ Apr 17
    • eval-callback/ Apr 27
    • gen-docs/ Aug 3
    • gguf/ Mar 4
    • gguf-hash/ Aug 18
    • idle/ Apr 17
      • CMakeLists.txt Apr 17
      • idle.cpp Mar 31
      • README.md Dec 5, 2025
    • llama-eval/ Jul 8
    • llama.android/ May 22
    • llama.swiftui/ Jun 6, 2025
    • lookahead/ Apr 17
    • lookup/ Aug 10
    • model-conversion/ Aug 11
    • parallel/ Apr 17
    • passkey/ Apr 17
    • retrieval/ Apr 17
    • rs-rollback/ Aug 27
    • simple/ Mar 4
    • simple-chat/ Mar 4
    • simple-cmake-pkg/ Dec 4, 2025
    • speculative/ Aug 10
    • speculative-simple/ Sep 16
    • sycl/ Aug 17
    • test-cmake/ Aug 14
    • training/ Jul 23
    • CMakeLists.txt Aug 27
    • convert_legacy_llama.py May 24
    • json_schema_pydantic_example.py Jul 7, 2024
    • json_schema_to_grammar.py Jun 20
    • llama.vim Mar 5
    • pydantic_models_to_grammar_examples.py May 2, 2025
    • pydantic_models_to_grammar.py Mar 21
    • reason-act.sh Jun 30, 2025
    • regex_to_grammar.py Jul 5, 2024
    • server_embd.py Apr 8, 2025
    • server-llama2-13B.sh Jun 30, 2025
    • ts-type-to-grammar.sh Jun 30, 2025
  • ggml/ Oct 13
  • gguf-py/ Sep 25
  • grammars/ Jun 14
  • include/ Sep 18
  • licenses/ Jan 14
  • media/ Sep 10, 2025
  • models/ Aug 15
  • patches/ Oct 18
  • pocs/ Apr 17
  • requirements/ Aug 11
  • scripts/ Aug 24
  • skills/ Aug 23
  • src/ Oct 13
  • tests/ Oct 18
  • tools/ Oct 18
  • vendor/ Aug 23
  • .clang-format Sep 16, 2025
  • .clang-tidy Sep 22, 2025
  • .dockerignore Jun 20
  • .ecrc Aug 27, 2024
  • .editorconfig May 16
  • .flake8 May 2, 2025
  • .gitignore Jun 12
  • .gitmodules Jul 3, 2025
  • .pre-commit-config.yaml May 3, 2024
  • AGENTS.md Aug 30
  • AUTHORS Aug 18
  • build-xcframework.sh Aug 18
  • CLAUDE.md Dec 29, 2025
  • CMakeLists.txt Sep 18
  • CMakePresets.json Jul 13, 2025
  • CODEOWNERS Jul 24
  • CONTRIBUTING.md Aug 30
  • convert_hf_to_gguf_update.py Jul 22
  • convert_hf_to_gguf.py Aug 2
  • convert_llama_ggml_to_gguf.py Mar 21
  • convert_lora_to_gguf.py Jun 14
  • flake.nix Aug 13, 2025
  • LICENSE Feb 2
  • Makefile Aug 20, 2025
  • mypy.ini
  • pyproject.toml Jun 2
  • pyrightconfig.json Mar 21
  • README.md Oct 18
  • requirements.txt Mar 5, 2025
  • SECURITY.md Aug 5
  • ty.toml May 20
languages
  • C++ 63%
  • C 14%
  • Python 8%
  • TypeScript 5%
  • GLSL 3%
  • Svelte 3%
  • other 4%
refs 2
main 8906fd8 Oct 18bolt 87e1b42 Oct 16
≡ llama-cpp-bonsai
readmetickets …commitspipelinessettings
idle/
idle/
examples/idle
new repository
sign in
sign in

llama.cpp/example/idle #

https://github.com/ggml-org/llama.cpp/pull/17766