Gentoo Packages

sci-misc/llama-cpp (guru)

Search

Install

Install this package:

emerge -a sci-misc/llama-cpp

Package Information

Description:
Port of Facebook's LLaMA model in C/C++
Homepage:
https://github.com/ggml-org/llama.cpp
License:
MIT

Versions

Version EAPI Keywords Slot
9999 8 ~amd64 0
0_pre9888 8 ~amd64 0
0_pre8838 8 ~amd64 0
0_pre8628 8 ~amd64 0
0_pre8198 8 ~amd64 0
0_pre7924 8 ~amd64 0
0_pre7611 8 ~amd64 0
0_pre7276 8 ~amd64 0
0_pre6980 8 ~amd64 0
0.3.0 8 ~amd64 0

Metadata

Maintainers

Upstream

Raw Metadata XML 
<pkgmetadata>
	<maintainer type="person">
		<email>negril.nx+gentoo@gmail.com</email>
		<name>Paul Zander</name>
	</maintainer>
	<use>
		<flag name="blis">Build a BLIS backend</flag>
		<flag name="flexiblas">Build a FlexiBLAS backend</flag>
		<flag name="rocm">Build a HIP (ROCm) backend</flag>
		<flag name="hip">Build a HIP (ROCm) backend</flag>
		<flag name="wmma">Use rocWMMA to enhance flash attention performance</flag>
		<flag name="openblas">Build an OpenBLAS backend</flag>
		<flag name="opencl">Build an OpenCL backend, so far only works on Adreno and Intel GPUs</flag>
		<flag name="openssl">Use openssl to support HTTPS</flag>
	</use>
	<upstream>
		<remote-id type="github">ggml-org/llama.cpp</remote-id>
	</upstream>
</pkgmetadata>

Lint Warnings

USE Flags

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

Flag Description 9999 0_pre9888 0_pre8838 0_pre8628 0_pre8198 0_pre7924 0_pre7611 0_pre7276 0_pre6980 0.3.0
blis Build a BLIS backend ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
cuda Enable NVIDIA CUDA support ⚠️ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
curl ⚠️ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
examples Also install wl-present ⚠️ ✓ ✓ ✓ ✓ ✓ ✓ ✗ ✗ ✗ ✓
flexiblas Build a FlexiBLAS backend ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
hip Build a HIP (ROCm) backend ✗ ✗ ✗ ✗ ✗ ✗ ✓ ✓ ✓ ✗
openblas Build an OpenBLAS backend ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
opencl Build an OpenCL backend, so far only works on Adreno and Intel GPUs ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
openmp Enable OpenMP parallel compression ⚠️ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕ ⊕
openssl Use openssl to support HTTPS ✓ ✓ ✓ ✗ ✗ ✗ ✗ ✗ ✗ ✓
rocm Build a HIP (ROCm) backend ✓ ✓ ✓ ✓ ✓ ✓ ✗ ✗ ✗ ✓
vulkan Build vulkan renderer ⚠️ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓ ✓
wmma Use rocWMMA to enhance flash attention performance ✓ ✓ ✓ ✓ ✓ ✓ ✗ ✗ ✗ ✓

Manifest

Type File Size Versions
DIST ggml-org_models_tinyllamas_stories15M-q4_0-99dd1a73db5a37100bd4ae633f4cfce6560e1567.gguf 19077344 bytes 9999, 0_pre9888, 0_pre8838, 0_pre8628, 0_pre8198, 0_pre7924, 0.3.0
DIST llama-cpp-0.3.0.tar.gz 36951021 bytes 0.3.0
DIST llama-cpp-0_pre6980.tar.gz 26431911 bytes 0_pre6980
DIST llama-cpp-0_pre7276.tar.gz 27765814 bytes 0_pre7276
DIST llama-cpp-0_pre7611.tar.gz 28622786 bytes 0_pre7611
DIST llama-cpp-0_pre7924.tar.gz 28899921 bytes 0_pre7924
DIST llama-cpp-0_pre8198.tar.gz 29091642 bytes 0_pre8198
DIST llama-cpp-0_pre8628.tar.gz 29611654 bytes 0_pre8628
DIST llama-cpp-0_pre8838.tar.gz 33811834 bytes 0_pre8838
DIST llama-cpp-0_pre9888.tar.gz 35116234 bytes 0_pre9888
Unmatched Entries
Type File Size