[ sid ]
[ ソース: llama.cpp ]
パッケージ: llama.cpp (8064+dfsg-2 など)
LLM inference in C/C++ - metapackage
The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide range of hardware - locally and in the cloud.
* Plain C/C++ implementation without any dependencies * Apple silicon is a first-class citizen - optimized via ARM NEON, Accelerate and Metal frameworks * AVX, AVX2, AVX512 and AMX support for x86 architectures * 1.5-bit, 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for faster inference and reduced memory use * Custom CUDA kernels for running LLMs on NVIDIA GPUs (support for AMD GPUs via HIP and Moore Threads MTT GPUs via MUSA) * Vulkan and SYCL backend support * CPU+GPU hybrid inference to partially accelerate models larger than the total VRAM capacity
The compute functionality is provided by ggml. By default, ggml's CPU backend is installed, but there are many other backends for CPUs and GPUs.
This is a meta-package that either depends on all of the relevant binary packages.
その他の llama.cpp 関連パッケージ
|
|
|
|
-
- dep: libc6.1 (>= 2.38) [alpha]
- GNU C ライブラリ: 共有ライブラリ
以下のパッケージによって提供される仮想パッケージでもあります: libc6.1-udeb
-
- dep: libcurl4t64 (>= 7.16.2) [alpha]
- 使いやすいクライアントサイドの URL 転送ライブラリ (OpenSSL フレーバ)
-
- dep: libgcc-s1 (>= 3.4) [alpha]
- GCC 共有ライブラリ
-
- dep: libggml-cpu (<< 0.0~git20250713) [alpha]
- Tensor library for machine learning - CPU backend
- または libggml-backend (<< 0.0~git20250713)
- パッケージは利用できません
- dep: libggml-cpu (>= 0.0~git20250712) [alpha]
- または libggml-backend (>= 0.0~git20250712)
-
- dep: libstdc++6 (>= 14) [alpha]
- GNU 標準 C++ ライブラリ v3
-
- dep: llama.cpp-tools [all]
- LLM inference in C/C++ - main utilities
-
- dep: python3 [alpha]
- 対話式の高レベルオブジェクト指向言語 (デフォルト python3 バージョン)
-
- rec: llama.cpp-tools-extra
- LLM inference in C/C++ - extra utilities
-
- rec: python3-gguf
- Python library for working with GGUF files
-
- sug: llama.cpp-examples
- LLM inference in C/C++ - example programs