openKylin llama.cpp-riscv package

llama.cpp-riscv 9318-ok5 source package in openKylin

llama.cpp-riscv (9318-ok5) huanghe; urgency=medium

  * 安装Ubuntu拆分llama.cpp deb包

 -- like <email address hidden>  Fri, 03 Jul 2026 10:36:57 +0800

Series	Pocket	Published	Component	Section
Huanghe V3.0	proposed	on 2026-07-03	main	science

File	Size	SHA-256 Checksum
llama.cpp-riscv_9318.orig.tar.gz	32.4 MiB	3d76439a1c33f370e8a0ee7588f8a0f86d6698bb83083d9c694ed6e21f709bc0
llama.cpp-riscv_9318-ok5.debian.tar.xz	3.3 KiB	1617a460cb6526068b992037abdc3fa1367df5c0753afbdac0bc654e31767192
llama.cpp-riscv_9318-ok5.dsc	2.2 KiB	d36c56c4bf53db84d4e50ce8006c1c72aa52ea549c888baee262f5218cf70657

libggml-dev: Tensor library for machine learning - development files: ggml is a tensor library for machine learning that provides the compute
backend used by llama.cpp.
.
This package contains the ggml headers, CMake files and .so symlinks.

libggml0: Tensor library for machine learning - runtime (RVV build): ggml is a tensor library for machine learning that provides the compute
backend used by llama.cpp.
.
This package contains the ggml shared libraries and CPU backends, including
the RISC-V RVV (vector) CPU backend variant.

libllama-dev: LLM inference in C/C++ - headers and development files: llama.cpp enables LLM inference with minimal setup on a wide range of
hardware.
.
This package provides the llama.cpp library headers and development files.

libllama0: LLM inference in C/C++ - libraries (RVV build): llama.cpp enables LLM inference with minimal setup on a wide range of
hardware.
.
This package contains the libllama and libmtmd libraries. They are installed
to a private directory as they are not yet ABI-stable.

llama.cpp: LLM inference in C/C++ - metapackage (RVV build): llama.cpp enables LLM inference with minimal setup on a wide range of
hardware. This metapackage depends on the main llama.cpp utilities.
.
Built for RISC-V (openKylin huanghe) with the RVV vector extension enabled.

llama.cpp-examples: LLM inference in C/C++ - example programs (RVV build): llama.cpp enables LLM inference with minimal setup on a wide range of
hardware.
.
This package contains the utilities that upstream ships as examples.

llama.cpp-tests: LLM inference in C/C++ - tests (RVV build): llama.cpp enables LLM inference with minimal setup on a wide range of
hardware.
.
This package contains the test binaries.

llama.cpp-tools: LLM inference in C/C++ - main utilities (RVV build): llama.cpp enables LLM inference with minimal setup on a wide range of
hardware.
.
This package contains the most commonly used utilities: llama-cli,
llama-server, llama-bench and llama-quantize.

llama.cpp-tools-extra: LLM inference in C/C++ - extra utilities (RVV build): llama.cpp enables LLM inference with minimal setup on a wide range of
hardware.
.
This package contains all tools not already shipped in llama.cpp-tools.

python3-gguf: Python library for working with GGUF files: GGUF is a binary file format for storing models for inference with GGML and
executors based on GGML.
.
This package provides a Python library for reading and writing GGUF files,
plus a few CLI utilities.