Install this package:
emerge -a sci-ml/llama-cpp
If the package is masked, you can unmask it using the autounmask tool or standard emerge options:
autounmask sci-ml/llama-cpp
Or alternatively:
emerge --autounmask-write -a sci-ml/llama-cpp
<pkgmetadata> <maintainer type="person"> <email>me@puqns67.icu</email> <name>Puqns67</name> </maintainer> <use> <flag name="blis">Build a BLIS backend</flag> <flag name="flexiblas">Build a FlexiBLAS backend</flag> <flag name="openblas">Build an OpenBLAS backend</flag> <flag name="rocm">Build a HIP (ROCm) backend</flag> <flag name="wmma">Use rocWMMA to enhance flash attention performance</flag> <flag name="opencl">Build an OpenCL backend, so far only works on Adreno and Intel GPUs</flag> <flag name="rpc">Build with rpc-server</flag> <flag name="server">Build with example server</flag> </use> <upstream> <remote-id type="github">ggml-org/llama.cpp</remote-id> </upstream> </pkgmetadata>
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 | 9999 | 0_pre8583 |
|---|---|---|---|
| ${CPU_FLAGS[*]} | ⚠️ | ✓ | ✓ |
| blis | Build a BLIS backend | ✓ | ✓ |
| cuda | ⚠️ | ✓ | ✓ |
| examples | Build and install 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 | ⚠️ | ⊕ | ⊕ |
| rocm | Build a HIP (ROCm) backend | ✓ | ✓ |
| rpc | Build with rpc-server | ✓ | ✓ |
| server | Build with example server | ⊕ | ⊕ |
| vulkan | ⚠️ | ✓ | ✓ |
| wmma | Use rocWMMA to enhance flash attention performance | ✓ | ✓ |
| Type | File | Size | Versions |
|---|---|---|---|
| DIST | llama-cpp-0_pre8583.tar.gz | 29635898 bytes | 0_pre8583 |
| Type | File | Size |
|---|---|---|
| DIST | ggml-org_models_tinyllamas_stories15M-q4_0-99dd1a73db5a37100bd4ae633f4cfce6560e1567.gguf | 19077344 bytes |