Package: ggml Version: 0.0.1898-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 10 Depends: libggml0, libggml-cpu Filename: ./pool/sid/ml/1.1/ggml_0.0.1898-1_arm64.deb Size: 2912 SHA256: 346579b0edbdec9f23697d07f90e2800fe6ed11b9f3c90c1fcb6951ded1309ff Section: science Priority: optional Homepage: https://github.com/ggml-org/ Description: Tensor library for machine learning (metapackage) ggml is a pure C/C++ library implementing tensor computations used by neural networks. It is the basis for llama.cpp (large language models) and whisper.cpp (speech recognition) but can be used indepedently. This metapackage provides the minimal set of dependencies so that the library can actually be usable, since the dynamically-loaded CPU backend is required for most usages. Additional backends can be installed additionally, typically to support specific computing hardware such as GPUs. Package: ggml-dev Source: ggml Version: 0.0.1898-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 2212 Depends: libggml0 (= 0.0.1898-1), libggml-base0 (= 0.0.1898-1) Filename: ./pool/sid/ml/1.1/ggml-dev_0.0.1898-1_arm64.deb Size: 501216 SHA256: a0dab8165bfd97c9856549059b923050e624b3ccc628160c39db32147b0dd83c Section: libdevel Priority: optional Homepage: https://github.com/ggml-org/ Description: Tensor library for machine learning (development files) This developments package provides the files required to build software based on ggml. Package: libggml-base0 Source: ggml Version: 0.0.1898-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 533 Depends: libc6 (>= 2.38), libgcc-s1 (>= 3.0), libstdc++6 (>= 11) Filename: ./pool/sid/ml/1.1/libggml-base0_0.0.1898-1_arm64.deb Size: 172972 SHA256: e9dd9d0b7fce332c5995e574853184e1bb4628cac7787e621abe4ef78e009349 Section: libs Priority: optional Multi-Arch: same Homepage: https://github.com/ggml-org/ Description: Tensor library for machine learning (base) The ggml base library provides the backend-independent API upon which specialized libraries or applications can be built. Package: libggml-base0-dbgsym Source: ggml Version: 0.0.1898-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 1016 Depends: libggml-base0 (= 0.0.1898-1) Filename: ./pool/sid/ml/1.1/libggml-base0-dbgsym_0.0.1898-1_arm64.deb Size: 979928 SHA256: ee224f37de53cd79275f88f1b2a580282450c4be8fac7c825993c827f127c3de Section: debug Priority: optional Multi-Arch: same Description: debug symbols for libggml-base0 Build-Ids: 52221e5626ae5e80253a09a24d79c04d2aae9040 Package: libggml-blas Source: ggml Version: 0.0.1898-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 80 Depends: libc6 (>= 2.34), libgcc-s1 (>= 3.0), libggml-base0 (>= 0.0.1898), libopenblas0, libstdc++6 (>= 11), libggml0, libopenblas0-openmp, libopenblas64-0-openmp Filename: ./pool/sid/ml/1.1/libggml-blas_0.0.1898-1_arm64.deb Size: 14356 SHA256: a19720194fcd89e37abc2f3776cd8d522ccace82f3859db9ac20aa0c342b829c Section: science Priority: optional Multi-Arch: same Homepage: https://github.com/ggml-org/ Description: Tensor library for machine learning (OpenBLAS backend) The ggml BLAS backend provides software acceleration of the computations based on OpenBLAS. Package: libggml-blas-dbgsym Source: ggml Version: 0.0.1898-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 166 Depends: libggml-blas (= 0.0.1898-1) Filename: ./pool/sid/ml/1.1/libggml-blas-dbgsym_0.0.1898-1_arm64.deb Size: 138736 SHA256: 3c7d6e6b8e2122c56a927e0312540ba6ff0e6c01eeca92b31585a91c6036a8cf Section: debug Priority: optional Multi-Arch: same Description: debug symbols for libggml-blas Build-Ids: 6b4c82bb1e26d7259d6382c03874ff2107ff11af Package: libggml-cpu Source: ggml Version: 0.0.1898-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 464 Depends: libc6 (>= 2.34), libgcc-s1 (>= 3.0), libggml-base0 (>= 0.0.1898), libgomp1 (>= 4.9), libstdc++6 (>= 5.2), libggml0 Filename: ./pool/sid/ml/1.1/libggml-cpu_0.0.1898-1_arm64.deb Size: 144776 SHA256: 5905716a364f592558203090e0c0049300b1e2b37307c6e64411391c92b9ae82 Section: science Priority: optional Multi-Arch: same Homepage: https://github.com/ggml-org/ Description: Tensor library for machine learning (CPU backend) The ggml CPU backend provides computations based solely on plain CPU, without software or hardware acceleration. It is available as a set of dynamically loaded libraries optimized for various CPU families, depending on their specific capabilities. The ggml library will automatically select the most appropriate one, allowing one to run computations on older CPU while still benefiting from the capabilities of recent ones. Package: libggml-cpu-dbgsym Source: ggml Version: 0.0.1898-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 672 Depends: libggml-cpu (= 0.0.1898-1) Filename: ./pool/sid/ml/1.1/libggml-cpu-dbgsym_0.0.1898-1_arm64.deb Size: 646080 SHA256: 816eece5cf632173b46b37b70dce65f0dd75c2131cd9f326df3314707f01263c Section: debug Priority: optional Multi-Arch: same Description: debug symbols for libggml-cpu Build-Ids: 520dcf39a989daf4a5eccfcdfc08301f7711320c Package: libggml-rpc Source: ggml Version: 0.0.1898-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 144 Depends: libc6 (>= 2.38), libgcc-s1 (>= 3.0), libggml-base0 (>= 0.0.1898), libstdc++6 (>= 11), libggml0 Filename: ./pool/sid/ml/1.1/libggml-rpc_0.0.1898-1_arm64.deb Size: 27700 SHA256: 86cc94438a46c809c9bc6e8a2724e5233a70e2288763dd8133b3535b12aecfe5 Section: science Priority: optional Multi-Arch: same Homepage: https://github.com/ggml-org/ Description: Tensor library for machine learning (RPC backend) The ggml RPC backend allows one to distribute computations over the network on remote ggml backends. Package: libggml-rpc-dbgsym Source: ggml Version: 0.0.1898-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 425 Depends: libggml-rpc (= 0.0.1898-1) Filename: ./pool/sid/ml/1.1/libggml-rpc-dbgsym_0.0.1898-1_arm64.deb Size: 405480 SHA256: df505b082809d18de202d6ccc9674fcddb8481f9d2ec6b47a7eb4bcc541301f0 Section: debug Priority: optional Multi-Arch: same Description: debug symbols for libggml-rpc Build-Ids: ec44a0775da8b1c76da35e0f351dfedb8135b9c0 Package: libggml-vulkan Source: ggml Version: 0.0.1898-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 25339 Depends: libc6 (>= 2.38), libgcc-s1 (>= 3.0), libggml-base0 (>= 0.0.1898), libstdc++6 (>= 13.1), libvulkan1 (>= 1.2.131.2), libggml0 Filename: ./pool/sid/ml/1.1/libggml-vulkan_0.0.1898-1_arm64.deb Size: 1740428 SHA256: d07edcb73182ab708919219276f463c8e0efa8f3fecdbf2737d7f1b2081ca6c4 Section: science Priority: optional Multi-Arch: same Homepage: https://github.com/ggml-org/ Description: Tensor library for machine learning (Vulkan backend) The ggml Vulkan backend provides hardware acceleration of the computations based on the Vulkan API. This is typically used to leverage GPU parallel computations capabilities. Package: libggml-vulkan-dbgsym Source: ggml Version: 0.0.1898-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 2732 Depends: libggml-vulkan (= 0.0.1898-1) Filename: ./pool/sid/ml/1.1/libggml-vulkan-dbgsym_0.0.1898-1_arm64.deb Size: 2577404 SHA256: 15394c3c4c72a0eab10903e49c07cab6ef05be0a835002329d00b880f2dbeb8b Section: debug Priority: optional Multi-Arch: same Description: debug symbols for libggml-vulkan Build-Ids: f67c4f17e416cc7f34933f78c426116c74ab71e0 Package: libggml0 Source: ggml Version: 0.0.1898-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 84 Depends: libc6 (>= 2.34), libgcc-s1 (>= 3.0), libggml-base0 (>= 0.0.1898), libstdc++6 (>= 9) Filename: ./pool/sid/ml/1.1/libggml0_0.0.1898-1_arm64.deb Size: 14716 SHA256: 4d724f72e98c7cca960fff99e10d29995ae705873935dca06d9a41422d8ffd13 Section: libs Priority: optional Multi-Arch: same Homepage: https://github.com/ggml-org/ Description: Tensor library for machine learning (loader) The ggml library is a thin high-level layer mostly responsible for loading the various ggml backends, and connect them to the API provided by the ggml base library. Package: libggml0-dbgsym Source: ggml Version: 0.0.1898-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 237 Depends: libggml0 (= 0.0.1898-1) Filename: ./pool/sid/ml/1.1/libggml0-dbgsym_0.0.1898-1_arm64.deb Size: 224264 SHA256: 818938a2b570a2261d32147fa95e486b03a9d52a3c503f9ed2d7758e4102f5c5 Section: debug Priority: optional Multi-Arch: same Description: debug symbols for libggml0 Build-Ids: 851e858c1046318366fa4b44cff3362af8391e48 Package: libllama0 Source: llama-cpp Version: 0.0.5028-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 1559 Depends: libc6 (>= 2.38), libgcc-s1 (>= 3.0), libggml-base0 (>= 0.0.1898), libggml0 (>= 0.0.1898), libstdc++6 (>= 11) Filename: ./pool/sid/ml/1.1/libllama0_0.0.5028-1_arm64.deb Size: 411176 SHA256: 53360f27d9e389cab35cb750be317783699389f2c885031093a25eb2971d20e7 Section: libs Priority: optional Multi-Arch: same Homepage: https://github.com/ggml-org/llama.cpp Description: Inference of large language models in pure C/C++ (shared library) llama.cpp leverages the ggml tensor library in order to run large language models (LLMs) provided in the GGUF file format. Package: libllama0-dbgsym Source: llama-cpp Version: 0.0.5028-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 7707 Depends: libllama0 (= 0.0.5028-1) Filename: ./pool/sid/ml/1.1/libllama0-dbgsym_0.0.5028-1_arm64.deb Size: 7626296 SHA256: 6f3f36fb8d59f0d30b2414d66c9b82244a584a4841ecdc03c42003a48c13ac14 Section: debug Priority: optional Multi-Arch: same Description: debug symbols for libllama0 Build-Ids: 6918cd59ed1c6df718b9391f7c43deeb459d75dc Package: libllama0-dev Source: llama-cpp Version: 0.0.5028-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 96 Depends: ggml-dev, libllama0 (= 0.0.5028-1) Filename: ./pool/sid/ml/1.1/libllama0-dev_0.0.5028-1_arm64.deb Size: 18868 SHA256: c4a43473bf3ab17b255697234b61b9dbe3c0de7efe301b1222d2abffe756efe1 Section: libdevel Priority: optional Homepage: https://github.com/ggml-org/llama.cpp Description: Inference of large language models in pure C/C++ (development files) Development files required for building software based on the stable and documented llama.cpp API. Package: libwhisper1 Source: whisper-cpp Version: 1.7.5-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 470 Depends: libc6 (>= 2.32), libgcc-s1 (>= 3.0), libggml-base0 (>= 0.0.1898), libggml0 (>= 0.0.1898), libstdc++6 (>= 11), libggml-cpu Filename: ./pool/sid/ml/1.1/libwhisper1_1.7.5-1_arm64.deb Size: 145400 SHA256: 489f8c5ed2ffc74082f90b43f87e4f78a697a66e508b1ff50e7a1cd415f865c2 Section: libs Priority: optional Multi-Arch: same Homepage: https://github.com/ggerganov/whisper.cpp Description: Inference of Whisper in pure C/C++ (shared library) The shared library provides the core of whisper.cpp speech-to-text capabilities using a Whisper model. Package: libwhisper1-dbgsym Source: whisper-cpp Version: 1.7.5-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 2075 Depends: libwhisper1 (= 1.7.5-1) Filename: ./pool/sid/ml/1.1/libwhisper1-dbgsym_1.7.5-1_arm64.deb Size: 2031428 SHA256: 0a2172cb329bb69e9c7ca7e290ad6b5ca46fd5666c1ad04aeb5d1b86faa44df4 Section: debug Priority: optional Multi-Arch: same Description: debug symbols for libwhisper1 Build-Ids: c90729831d326c069569de87f4407871dc6eb1e8 Package: libwhisper1-dev Source: whisper-cpp Version: 1.7.5-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 56 Depends: ggml-dev, libwhisper1 (= 1.7.5-1) Filename: ./pool/sid/ml/1.1/libwhisper1-dev_1.7.5-1_arm64.deb Size: 10968 SHA256: 04d1385076fd3f1278a55523ebaf2ab04a56b21291d0719d7af6425b214421c0 Section: libdevel Priority: optional Multi-Arch: same Homepage: https://github.com/ggerganov/whisper.cpp Description: Inference of Whisper in pure C/C++ (development files) Development files for using whisper.cpp as a shared library in applications. Package: llama-cpp-dev Source: llama-cpp Version: 0.0.5028-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 5571 Depends: libllama0-dev (= 0.0.5028-1), libcurl4-openssl-dev, libssl-dev Filename: ./pool/sid/ml/1.1/llama-cpp-dev_0.0.5028-1_arm64.deb Size: 700916 SHA256: 50ec5a8a39f6d8a1cc48fd8e7b15335617597f8fd750e23a3f737c0efecc6251 Section: libdevel Priority: optional Homepage: https://github.com/ggml-org/llama.cpp Description: Inference of large language models in pure C/C++ (common static library) Development files and static library providing a framework command to the various examples. It allows one to quickly to develop a command line utility but is expected to provide a less stable API than libllama-dev. Package: llama-cpp-tools Source: llama-cpp Version: 0.0.5028-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 2269 Depends: libc6 (>= 2.38), libcurl4t64 (>= 7.16.2), libgcc-s1 (>= 3.0), libggml-base0 (>= 0.0.1898), libggml0 (>= 0.0.1898), libllama0 (>= 0.0.5028), libstdc++6 (>= 14), ggml, curl Filename: ./pool/sid/ml/1.1/llama-cpp-tools_0.0.5028-1_arm64.deb Size: 560680 SHA256: 5b4db6b525f9a1c3c90590a1aae538c55d9ea6562a866eea45c20e990abd9e80 Section: science Priority: optional Homepage: https://github.com/ggml-org/llama.cpp Description: Inference of large language models in pure C/C++ (tools) llama-cli: versatile tool wrapping most features provided by libllama. It typically allows one to run one-shot prompts or to "chat" with a large language model. . llama-quantize: utility to "quantize" a large language model GGUF file. Quantizing is the process of reducing the precision of the underlying neural-network at aminimal cost to its accuracy. . llama-bench: benchmarking of large language models or ggml backends. Package: llama-cpp-tools-dbgsym Source: llama-cpp Version: 0.0.5028-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 14014 Depends: llama-cpp-tools (= 0.0.5028-1) Filename: ./pool/sid/ml/1.1/llama-cpp-tools-dbgsym_0.0.5028-1_arm64.deb Size: 11617384 SHA256: 680a1c9085f1079d706fd29c7022ce64cfeb4ddff851be52e9c0e20080a0ee4d Section: debug Priority: optional Description: debug symbols for llama-cpp-tools Build-Ids: 6b34ad93b1f3e0c511a491e5ad53fcf813a1da13 70b820398b021dde89d8f56b9dbc6e127ef0bf41 f1faa27705f70b66af61c66af6934d9e1f88450f Package: whisper-cpp-cli Source: whisper-cpp Version: 1.7.5-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 851 Depends: libc6 (>= 2.38), libgcc-s1 (>= 3.0), libggml0 (>= 0.0.1898), libstdc++6 (>= 11), libwhisper1 (>= 1.7.5) Filename: ./pool/sid/ml/1.1/whisper-cpp-cli_1.7.5-1_arm64.deb Size: 290712 SHA256: d511f2f2d26a9c31383e77931f5e89afeb566c612aaa5b3f378eec909325050f Section: science Priority: optional Homepage: https://github.com/ggerganov/whisper.cpp Description: Inference of Whisper in pure C/C++ (CLI) A versatile tool giving command line access to most whisper-cpp capabilities. Package: whisper-cpp-cli-dbgsym Source: whisper-cpp Version: 1.7.5-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 3070 Depends: whisper-cpp-cli (= 1.7.5-1) Filename: ./pool/sid/ml/1.1/whisper-cpp-cli-dbgsym_1.7.5-1_arm64.deb Size: 2211820 SHA256: 6a1f8e9a1fb33e5c736a0b07ba6bbd262a16a128919f3700d1b0e8d0e76fdd0b Section: debug Priority: optional Description: debug symbols for whisper-cpp-cli Build-Ids: 572f3bbff42b633b10cde41d6b2a015533abb7cb Package: whisper-cpp-dev Source: whisper-cpp Version: 1.7.5-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 1573 Depends: libwhisper1-dev (= 1.7.5-1) Filename: ./pool/sid/ml/1.1/whisper-cpp-dev_1.7.5-1_arm64.deb Size: 327288 SHA256: b1d6034edc14ad6f618ced3be3bf3aeb1e1ca676a2e6da25088ad77d1ee0f925 Section: libdevel Priority: optional Homepage: https://github.com/ggerganov/whisper.cpp Description: Inference of Whisper in pure C/C++ (common static library) Development files and static libraries of the used to build the tools. These components speeds up the development but are likely to have less stable APIs. Package: whisper-cpp-stream Source: whisper-cpp Version: 1.7.5-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 787 Depends: libc6 (>= 2.38), libgcc-s1 (>= 3.0), libsdl2-2.0-0 (>= 2.0.12), libstdc++6 (>= 11), libwhisper1 (>= 1.7.5) Filename: ./pool/sid/ml/1.1/whisper-cpp-stream_1.7.5-1_arm64.deb Size: 269184 SHA256: 8835594faccdc60915ce4e29b3981eeeb8239fb06c3f3f13b1c563d03790b6cc Section: science Priority: optional Homepage: https://github.com/ggerganov/whisper.cpp Description: Inference of Whisper in pure C/C++ (stream) Real-time speech-to-text of SDL sound input. The SDL sound input (typically a microphone) is transcribed as text to the standard output. Package: whisper-cpp-stream-dbgsym Source: whisper-cpp Version: 1.7.5-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 2701 Depends: whisper-cpp-stream (= 1.7.5-1) Filename: ./pool/sid/ml/1.1/whisper-cpp-stream-dbgsym_1.7.5-1_arm64.deb Size: 1915948 SHA256: 1847355973641964bbadfe0a9a7c172ee6a1a97d0d1752acabfba83b2fc04d46 Section: debug Priority: optional Description: debug symbols for whisper-cpp-stream Build-Ids: eee81e924fad8bf07b08848398c374c425a0cebe Package: whisper-cpp-talk-llama Source: whisper-cpp Version: 1.7.5-1 Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 788 Depends: libc6 (>= 2.38), libgcc-s1 (>= 3.0), libggml-base0 (>= 0.0.1898), libggml0 (>= 0.0.1898), libllama0 (>= 0.0.5028), libsdl2-2.0-0 (>= 2.0.12), libstdc++6 (>= 11), libwhisper1 (>= 1.7.5), espeak-ng, libswresample4, libavcodec59, libavformat59 Filename: ./pool/sid/ml/1.1/whisper-cpp-talk-llama_1.7.5-1_arm64.deb Size: 278372 SHA256: 8587a17f37b8c9b3dd504de307388cd62d4ca687284454339e5e49076642d25f Section: science Priority: optional Homepage: https://github.com/ggerganov/whisper.cpp Description: Inference of Whisper in pure C/C++ (talk-llama) A tool allowing one to "talk" with a large language model, using llama.cpp. The SDL input (typically from a microphone) is translated into text by whisper.cpp and sent to llama.cpp for processing. Package: whisper-cpp-talk-llama-dbgsym Source: whisper-cpp Version: 1.7.5-1 Auto-Built-Package: debug-symbols Architecture: arm64 Maintainer: Mathieu Baudier Installed-Size: 3300 Depends: whisper-cpp-talk-llama (= 1.7.5-1) Filename: ./pool/sid/ml/1.1/whisper-cpp-talk-llama-dbgsym_1.7.5-1_arm64.deb Size: 2487616 SHA256: 4739ec362c49ed2e927f5fe114e65dce05bb2701fef71b6c359b62dcf146c626 Section: debug Priority: optional Description: debug symbols for whisper-cpp-talk-llama Build-Ids: 459b8def1e1a829da79b55b4cbe14a45228831fa