sci-ml/llama-cpp (zGentoo)

Search

Install

Install this package:

emerge -a sci-ml/llama-cpp

Package Information

Description:
LLM inference in C/C++ (GGML/GGUF) — CPU + optional GPU backends
Homepage:
https://github.com/ggml-org/llama.cpp
License:
MIT

Versions

Version EAPI Keywords Slot
12257 8 ~amd64 0

Metadata

No metadata available.

Lint Warnings

USE Flags

Manage flags for this package: euse -i <flag> -p sci-ml/llama-cpp | euse -E <flag> -p sci-ml/llama-cpp | euse -D <flag> -p sci-ml/llama-cpp

Flag Description 12257
blis ⚠️ ✓
cpu_flags_x86_avx ⚠️ ✓
cpu_flags_x86_avx2 ⚠️ ✓
cpu_flags_x86_avx512_bf16 ⚠️ ✓
cpu_flags_x86_avx512_vnni ⚠️ ✓
cpu_flags_x86_avx512f ⚠️ ✓
cpu_flags_x86_avx512vbmi ⚠️ ✓
cpu_flags_x86_avx_vnni ⚠️ ✓
cpu_flags_x86_bmi2 ⚠️ ✓
cpu_flags_x86_f16c ⚠️ ✓
cpu_flags_x86_fma3 ⚠️ ✓
cuda Enable NVIDIA Cuda computations support (Experimental!) ⚠️ ✓
curl ⚠️ ✓
examples Build examples ⚠️ ✓
flexiblas ⚠️ ✓
openblas ⚠️ ✓
opencl ⚠️ ✓
openmp ⚠️ ⊕
openssl ⚠️ ✓
rocm ⚠️ ✓
vulkan Enable experimental Vulkan backend ⚠️ ✓
wmma ⚠️ ✓

Files

Manifest

Type File Size Versions
DIST ggml-org_models_tinyllamas_stories15M-q4_0-99dd1a73db5a37100bd4ae633f4cfce6560e1567.gguf 19077344 bytes 12257
DIST llama-cpp-12257.gh.tar.gz 39188225 bytes 12257
Unmatched Entries
Type File Size
AUX llama-server.conf 1123 bytes
AUX llama-server.service 1610 bytes
EBUILD llama-cpp-12257.ebuild 7156 bytes