Install this package:
emerge -a localai-backend/llama-cpp
| Version | EAPI | Keywords | Slot |
|---|---|---|---|
| 4.12.1 | 8 | ~amd64 |
<pkgmetadata> <maintainer type="person"> <email>plamen@ipnmod.org</email> <name>Plamen K. Kosseff</name> </maintainer> <use> <flag name="native">Let the bundled ggml library auto-detect the build host's CPU features (-march=native) instead of relying on CFLAGS</flag> <flag name="openblas">CPU BLAS acceleration via <pkg>sci-libs/openblas</pkg></flag> <flag name="rocm">GPU acceleration on AMD via ROCm/HIP</flag> <flag name="vulkan">GPU acceleration via Vulkan</flag> </use> <upstream> <remote-id type="github">mudler/LocalAI</remote-id> </upstream> </pkgmetadata>
Manage flags for this package:
euse -i <flag> -p localai-backend/llama-cpp |
euse -E <flag> -p localai-backend/llama-cpp |
euse -D <flag> -p localai-backend/llama-cpp
| Flag | Description | 4.12.1 |
|---|---|---|
| test | ⚠️ | ✓ |
| Type | File | Size | Versions |
|---|---|---|---|
| DIST | llama.cpp-c0fd78626405c6d9b934efef0ec7291fcc20e3d6.tar.gz | 38326539 bytes | 4.12.1 |
| Type | File | Size |
|---|---|---|
| DIST | localai-4.12.1.tar.gz | 30086342 bytes |
| EBUILD | llama-cpp-4.12.1.ebuild | 3036 bytes |
| MISC | metadata.xml | 697 bytes |