Package: mingw-w64-x86_64-llama.cpp

Source Files

View Changes

View Issues

Report Issue

Base Package:

mingw-w64-llama.cpp

Description:

Port of Facebook's LLaMA model in C/C++ (mingw-w64)

Group(s):

Repo:

mingw64

Homepage:

https://github.com/ggerganov/llama.cpp

License(s):

MIT

Version:

r2859.7bd4ffb78-1 (b3091.r0.g2b33896-1 in git)

External:

Anitya: llama.cpp
AUR: r1110.423db74
Repology: llama.cpp

Installation:

pacman -S mingw-w64-x86_64-llama.cpp

File:

https://mirror.msys2.org/mingw/mingw64/mingw-w64-x86_64-llama.cpp-r2859.7bd4ffb78-1-any.pkg.tar.zst

SHA256:

8e197e060160f788357902211b31a8bab12570255ac1d934e51ecc27cf75cc54

Last Packager:

CI (msys2/msys2-autobuild/9c7e8d31/9047279075)

Build Date:

2024-05-12 00:09:37

Package Size:

3.26 MB

Installed Size:

29.40 MB

Source-Only Tarball:

https://mirror.msys2.org/mingw/sources/mingw-w64-llama.cpp-r2859.7bd4ffb78-1.src.tar.zst

Dependencies:

Optional Dependencies:

Build Dependencies:

Check Dependencies:

Provides:

Conflicts:

Replaces:

Provided By:

Required By:

Files:

/mingw64/bin/libggml_shared.dll
/mingw64/bin/libllama.dll
/mingw64/bin/libllava_shared.dll
/mingw64/bin/llama.cpp-baby-llama.exe
/mingw64/bin/llama.cpp-batched-bench.exe
/mingw64/bin/llama.cpp-batched.exe
/mingw64/bin/llama.cpp-beam-search.exe
/mingw64/bin/llama.cpp-benchmark.exe
/mingw64/bin/llama.cpp-convert-llama2c-to-ggml.exe
/mingw64/bin/llama.cpp-convert-lora-to-ggml.py
/mingw64/bin/llama.cpp-convert.py
/mingw64/bin/llama.cpp-embedding.exe
/mingw64/bin/llama.cpp-eval-callback.exe
/mingw64/bin/llama.cpp-export-lora.exe
/mingw64/bin/llama.cpp-finetune.exe
/mingw64/bin/llama.cpp-gguf-split.exe
/mingw64/bin/llama.cpp-gguf.exe
/mingw64/bin/llama.cpp-gritlm.exe
/mingw64/bin/llama.cpp-imatrix.exe
/mingw64/bin/llama.cpp-infill.exe
/mingw64/bin/llama.cpp-llama-bench.exe
/mingw64/bin/llama.cpp-llava-cli.exe
/mingw64/bin/llama.cpp-lookahead.exe
/mingw64/bin/llama.cpp-lookup-create.exe
/mingw64/bin/llama.cpp-lookup-merge.exe
/mingw64/bin/llama.cpp-lookup-stats.exe
/mingw64/bin/llama.cpp-lookup.exe
/mingw64/bin/llama.cpp-parallel.exe
/mingw64/bin/llama.cpp-passkey.exe
/mingw64/bin/llama.cpp-perplexity.exe
/mingw64/bin/llama.cpp-quantize-stats.exe
/mingw64/bin/llama.cpp-quantize.exe
/mingw64/bin/llama.cpp-retrieval.exe
/mingw64/bin/llama.cpp-save-load-state.exe
/mingw64/bin/llama.cpp-server.exe
/mingw64/bin/llama.cpp-simple.exe
/mingw64/bin/llama.cpp-speculative.exe
/mingw64/bin/llama.cpp-test-autorelease.exe
/mingw64/bin/llama.cpp-test-backend-ops.exe
/mingw64/bin/llama.cpp-test-chat-template.exe
/mingw64/bin/llama.cpp-test-grad0.exe
/mingw64/bin/llama.cpp-test-grammar-integration.exe
/mingw64/bin/llama.cpp-test-grammar-parser.exe
/mingw64/bin/llama.cpp-test-json-schema-to-grammar.exe
/mingw64/bin/llama.cpp-test-llama-grammar.exe
/mingw64/bin/llama.cpp-test-model-load-cancel.exe
/mingw64/bin/llama.cpp-test-quantize-fns.exe
/mingw64/bin/llama.cpp-test-quantize-perf.exe
/mingw64/bin/llama.cpp-test-rope.exe
/mingw64/bin/llama.cpp-test-sampling.exe
/mingw64/bin/llama.cpp-test-tokenizer-0.exe
/mingw64/bin/llama.cpp-test-tokenizer-1-bpe.exe
/mingw64/bin/llama.cpp-test-tokenizer-1-spm.exe
/mingw64/bin/llama.cpp-tokenize.exe
/mingw64/bin/llama.cpp-train-text-from-scratch.exe
/mingw64/bin/llama.cpp.exe
/mingw64/include/ggml-alloc.h
/mingw64/include/ggml-backend.h
/mingw64/include/ggml.h
/mingw64/include/llama.h
/mingw64/lib/cmake/Llama/LlamaConfig.cmake
/mingw64/lib/cmake/Llama/LlamaConfigVersion.cmake
/mingw64/lib/libggml_shared.dll.a
/mingw64/lib/libllama.dll.a
/mingw64/lib/libllava_shared.dll.a
/mingw64/share/licenses/llama.cpp/LICENSE