Search Criteria
Package Details: llama.cpp-vulkan-gemma4 b8763-2
Package Actions
| Git Clone URL: | https://aur.archlinux.org/llama.cpp-vulkan-gemma4.git (read-only, click to copy) |
|---|---|
| Package Base: | llama.cpp-vulkan-gemma4 |
| Description: | Port of Facebook's LLaMA model in C/C++ (Vulkan, Gemma 4 model fixes) |
| Upstream URL: | https://github.com/ggml-org/llama.cpp |
| Licenses: | MIT |
| Conflicts: | ggml, libggml, llama.cpp, stable-diffusion.cpp |
| Provides: | ggml, libggml, llama.cpp |
| Submitter: | ewout |
| Maintainer: | ewout |
| Last Packager: | ewout |
| Votes: | 1 |
| Popularity: | 0.51 |
| First Submitted: | 2026-04-12 05:10 (UTC) |
| Last Updated: | 2026-04-12 05:11 (UTC) |
Dependencies (15)
- curl (curl-gitAUR, curl-c-aresAUR)
- gcc-libs (gcc-libs-gitAUR, gccrs-libs-gitAUR, gcc-libs-snapshotAUR)
- glibc (glibc-gitAUR, glibc-eacAUR, glibc-git-native-pgoAUR)
- python
- vulkan-icd-loader (vulkan-icd-loader-gitAUR)
- cmake (cmake3AUR, cmake-gitAUR) (make)
- git (git-gitAUR, git-glAUR, git-wd40AUR) (make)
- shaderc (shaderc-gitAUR, shaderc-gitAUR) (make)
- vulkan-headers (vulkan-headers-gitAUR) (make)
- python-ggufAUR (python-gguf-gitAUR) (optional) – needed for convert_hf_to_gguf.py
- python-numpy (python-numpy-gitAUR, python-numpy-mkl-binAUR, python-numpy1AUR, python-numpy-mkl-tbbAUR, python-numpy-mklAUR) (optional) – needed for convert_hf_to_gguf.py
- python-pytorch (python-pytorch-cuda12.9AUR, python-pytorch-opt-cuda12.9AUR, python-pytorch-cuda, python-pytorch-opt, python-pytorch-opt-cuda, python-pytorch-opt-rocm, python-pytorch-rocm) (optional) – needed for convert_hf_to_gguf.py
- python-safetensors (optional) – needed for convert_hf_to_gguf.py
- python-sentencepieceAUR (python-sentencepiece-gitAUR, python-sentencepiece-binAUR) (optional) – needed for convert_hf_to_gguf.py
- python-transformersAUR (python-transformers-gitAUR) (optional) – needed for convert_hf_to_gguf.py
Required by (5)
- llamaman-bin (requires llama.cpp) (optional)
- scmd-bin (requires llama.cpp)
- voxd (requires llama.cpp) (optional)
- voxd-bin (requires llama.cpp) (optional)
- voxd-git (requires llama.cpp) (optional)
Sources (9)
- 0001-chat-use-AST-only-path-for-Gemma-4-tool-call-parsing.patch
- 0002-chat-add-end-of-turn-stop-sequence-for-Gemma-4.patch
- 0003-templates-fix-Gemma-4-template-crash-on-array-typed-.patch
- 0004-tests-add-Gemma-4-edge-case-tests-for-tool-calls-and.patch
- 0005-common-add-FC-format-validation-reference-for-Gemma-.patch
- 0006-server-add-Gemma-4-reasoning-control-in-web-UI.patch
- https://raw.githubusercontent.com/Orion-zhen/aur-packages/refs/heads/main/assets/llama.cpp/llama.cpp.conf
- https://raw.githubusercontent.com/Orion-zhen/aur-packages/refs/heads/main/assets/llama.cpp/llama.cpp.service
- llama.cpp-b8763.tar.gz