Gentoo Packages

Search

Install

Install this package:

emerge -a sci-misc/llama-cpp

If the package is masked, you can unmask it using the autounmask tool or standard emerge options:

autounmask sci-misc/llama-cpp

Or alternatively:

emerge --autounmask-write -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_pre8838	8	~amd64	0

Metadata

Maintainers

Sergey Alirzaev (zl29ah@gmail.com) - Type: person

Upstream

Remote IDs:
- github: ggml-org/llama.cpp

Raw Metadata XML

<pkgmetadata>
	<maintainer type="person">
		<email>zl29ah@gmail.com</email>
		<name>Sergey Alirzaev</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

[Warning] USE flag 'curl' in ebuild 9999 is not documented in metadata.xml
[Warning] USE flag 'openmp' in ebuild 9999 is not documented in metadata.xml
[Warning] USE flag 'cuda' in ebuild 9999 is not documented in metadata.xml
[Warning] USE flag 'vulkan' in ebuild 9999 is not documented in metadata.xml
[Warning] USE flag 'examples' in ebuild 9999 is not documented in metadata.xml
[Warning] USE flag 'curl' in ebuild 0_pre8838 is not documented in metadata.xml
[Warning] USE flag 'openmp' in ebuild 0_pre8838 is not documented in metadata.xml
[Warning] USE flag 'cuda' in ebuild 0_pre8838 is not documented in metadata.xml
[Warning] USE flag 'vulkan' in ebuild 0_pre8838 is not documented in metadata.xml
[Warning] USE flag 'examples' in ebuild 0_pre8838 is not documented in metadata.xml
[Error] Missing md5-cache for ebuild llama-cpp-9999
[Error] Missing md5-cache for ebuild llama-cpp-0_pre8838

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_pre8838
blis	Build a BLIS backend	✓	✓
cuda	Enable NVIDIA CUDA support ⚠️	✓	✓
curl	Use curl for http,https and ftp backends ⚠️	✓	✓
examples	⚠️	✓	✓
flexiblas	Build a FlexiBLAS backend	✓	✓
openblas	Build an OpenBLAS backend	✓	✓
opencl	Build an OpenCL backend, so far only works on Adreno and Intel GPUs	✓	✓
openmp	⚠️	⊕	⊕
openssl	Use openssl to support HTTPS	✓	✓
rocm	Build a HIP (ROCm) backend	✓	✓
vulkan	⚠️	✓	✓
wmma	Use rocWMMA to enhance flash attention performance	✓	✓

Manifest

Type	File	Size	Versions
DIST	llama-cpp-0_pre8838.tar.gz	33811834 bytes	0_pre8838

Unmatched Entries

Type	File	Size
DIST	ggml-org_models_tinyllamas_stories15M-q4_0-99dd1a73db5a37100bd4ae633f4cfce6560e1567.gguf	19077344 bytes

sci-misc/llama-cpp (inode64-overlay)