Crandore Hub

llamaR

Interface for Large Language Models via 'llama.cpp'

Provides 'R' bindings to 'llama.cpp' for running Large Language Models ('LLMs') locally with optional 'Vulkan' GPU acceleration via 'ggmlR'. Supports model loading, text generation, 'tokenization', token-to-piece conversion, 'embeddings' (single and batch), encoder-decoder inference, low-level batch management, chat templates, 'LoRA' adapters, explicit backend/device selection, multi-GPU split, and 'NUMA' optimization. Includes a high-level 'ragnar'-compatible embedding provider ('embed_llamar'). Built on top of 'ggmlR' for efficient tensor operations.

Versions across snapshots

VersionRepositoryFileSize
0.2.3 rolling linux/jammy R-4.5 llamaR_0.2.3.tar.gz 1.4 MiB
0.2.3 rolling linux/noble R-4.5 llamaR_0.2.3.tar.gz 1.4 MiB
0.2.3 rolling source/ R- llamaR_0.2.3.tar.gz 480.6 KiB
0.2.3 latest linux/jammy R-4.5 llamaR_0.2.3.tar.gz 1.4 MiB
0.2.3 latest linux/noble R-4.5 llamaR_0.2.3.tar.gz 1.4 MiB
0.2.3 latest source/ R- llamaR_0.2.3.tar.gz 480.6 KiB
0.2.3 2026-04-26 source/ R- llamaR_0.2.3.tar.gz 480.6 KiB
0.2.3 2026-04-23 source/ R- llamaR_0.2.3.tar.gz 480.6 KiB
0.2.3 2026-04-09 windows/windows R-4.5 llamaR_0.2.3.zip 1.7 MiB

Dependencies (latest)

Depends

Imports

LinkingTo

Suggests