Paquet : libllama0 (5882+dfsg-3)

Liens pour libllama0

Ressources Debian :

Télécharger le paquet source llama.cpp :

Responsables :

Ressources externes :

Page d'accueil [github.com]

Paquets similaires :

LLM inference in C/C++ - libraries

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 package contains the libllama and libmtmd libraries. Note that these libraries are not yet stable, so they are installed to private directories for now.

Autres paquets associés à libllama0

dépendances

recommandations

suggestions

enhances

dep: libc6 (>= 2.38)

bibliothèque C GNU : bibliothèques partagées
un paquet virtuel est également fourni par libc6-udeb
dep: libgcc-s1 (>= 3.0) [non riscv64]

bibliothèque de prise en charge de GCC

dep: libgcc-s1 (>= 4.3) [riscv64]
dep: libggml0 (>= 0.0~git20250712.d62df60)

Tensor library for machine learning - libraries
dep: libggml0-backend-cpu (<< 0.0~git20250713)

Tensor library for machine learning - CPU backend

dep: libggml0-backend-cpu (>= 0.0~git20250712)
dep: libstdc++6 (>= 11)

bibliothèque standard C++ de GNU v3

Télécharger libllama0

Télécharger pour toutes les architectures proposées
Architecture	Taille du paquet	Espace occupé une fois installé	Fichiers
amd64	730,5 ko	2 508,0 ko	[liste des fichiers]
arm64	646,2 ko	2 472,0 ko	[liste des fichiers]
ppc64el	731,0 ko	2 856,0 ko	[liste des fichiers]
riscv64	702,7 ko	1 924,0 ko	[liste des fichiers]
s390x	735,2 ko	2 640,0 ko	[liste des fichiers]