BSD Portsai/llama-cpp 9426 MidnightBSD
Facebook's LLaMA model in C/C++
- System
- MidnightBSD
- Repository
- mports
- Maintainer
- [email protected]
- Last update
- Commit
d5bd1a557b- License
- mit
- Categories
- ai
Description
The main goal of llama.cpp is to enable LLM inference with minimal setup and state-of-the-art performance on a wide variety of hardware - locally and in the cloud.
In the other systems
| System | Port | Version |
|---|---|---|
| MidnightBSD | ai/llama-cpp | 9426 |
| FreeBSD | misc/llama-cpp | 11669 |
| DragonFly | misc/llama-cpp | 3285 |
Install
Binary package:
mport install llama-cppFrom mports:
cd /usr/mports/ai/llama-cpp && make install cleanTo depend on this port in another port's Makefile:
RUN_DEPENDS= llama-cpp>0:ai/llama-cpp
LIB_DEPENDS= libggml-base.so:ai/llama-cppDependencies
As this port's Makefile names them.
Build 1
npm: www/npm
Fetch 2
npm: www/npm${LOCALBASE}/share/certs/ca-root-nss.crt: security/ca_root_nss
Build dependencies 2
No port depends on this one.
Configuration
Options name: ai_llama-cpp
| Option | Default | Description |
|---|---|---|
| EXAMPLES | on | |
| VULKAN | on | Vulkan GPU offload support |
- USES
- cmake:testing compiler:c++11-lang localbase python:run shebangfix ssl
- Service scripts
llama-server
Files
pkg-plist 101
- bin/llama
- bin/llama-batched
- bin/llama-batched-bench
- bin/llama-bench
- bin/llama-cli
- bin/llama-completion
- bin/llama-convert-llama2c-to-ggml
- bin/llama-cvector-generator
- bin/llama-debug
- bin/llama-debug-template-parser
- bin/llama-diffusion-cli
- bin/llama-embedding
- bin/llama-eval-callback
- bin/llama-export-lora
- bin/llama-finetune
- bin/llama-fit-params
- bin/llama-gen-docs
- bin/llama-gguf
- bin/llama-gguf-hash
- bin/llama-gguf-split
- bin/llama-idle
- bin/llama-imatrix
- bin/llama-lookahead
- bin/llama-lookup
- bin/llama-lookup-create
- bin/llama-lookup-merge
- bin/llama-lookup-stats
- bin/llama-mtmd-cli
- bin/llama-parallel
- bin/llama-passkey
- bin/llama-perplexity
- bin/llama-quantize
- bin/llama-results
- bin/llama-retrieval
- bin/llama-server
- bin/llama-simple
- bin/llama-simple-chat
- bin/llama-speculative
- bin/llama-speculative-simple
- bin/llama-template-analysis
- bin/llama-tokenize
- bin/llama-tts
- include/ggml-alloc.h
- include/ggml-backend.h
- include/ggml-blas.h
- include/ggml-cann.h
- include/ggml-cpp.h
- include/ggml-cpu.h
- include/ggml-cuda.h
- include/ggml-metal.h
- include/ggml-openvino.h
- include/ggml-opt.h
- include/ggml-rpc.h
- include/ggml-sycl.h
- include/ggml-virtgpu.h
- include/ggml-vulkan.h
- include/ggml-webgpu.h
- include/ggml-zendnn.h
- include/ggml.h
- include/gguf.h
- include/llama-cpp.h
- include/llama.h
- include/mtmd-debug.h
- include/mtmd-helper.h
- include/mtmd.h
- lib/cmake/ggml/ggml-config.cmake
- lib/cmake/ggml/ggml-version.cmake
- lib/cmake/llama/llama-config.cmake
- lib/cmake/llama/llama-version.cmake
- lib/libggml-base.so
- lib/libggml-base.so.0
- lib/libggml-base.so.
- lib/libggml-cpu.so
- lib/libggml-cpu.so.0
- lib/libggml-cpu.so.
- lib/libggml-vulkan.so
- lib/libggml-vulkan.so.0
- lib/libggml-vulkan.so.
- lib/libggml.so
- lib/libggml.so.0
- lib/libggml.so.
- lib/libllama-batched-bench-impl.so
- lib/libllama-bench-impl.so
- lib/libllama-cli-impl.so
- lib/libllama-common.so
- lib/libllama-common.so.0
- lib/libllama-common.so.0.0.
- lib/libllama-completion-impl.so
- lib/libllama-fit-params-impl.so
- lib/libllama-perplexity-impl.so
- lib/libllama-quantize-impl.so
- lib/libllama-server-impl.so
- lib/libllama.so
- lib/libllama.so.0
- lib/libllama.so.0.0.
- lib/libmtmd.so
- lib/libmtmd.so.0
- lib/libmtmd.so.0.0.
- libdata/pkgconfig/llama.pc
- @dir lib/cmake/ggml
The first 100 are listed.
distinfo 2
| File | Size | SHA256 |
|---|---|---|
| llama-cpp-9426/llama-ui-npm-9426.tar.gz | 6.8283814e+07 | d472fb606a4c2cfd365ffacba2e3ae49316a512199d09c41c9970aa395ea87f7 |
| llama-cpp-9426/ggml-org-llama.cpp-b9426_GH0.tar.gz | 3.3982934e+07 | a96658491547aa923980dbffc25179b0f1164ad3dab40126673414ebf947238c |