Sign me up Login

Details about package llama-cpp

Name:	llama-cpp
Uploader:	Mathieu Baudier <mbaudier@argeo.org> (Debian QA page)
Description:	libllama - Inference of LLMs in pure C/C++ (shared library) llama-cpp-cli - Inference of LLMs in pure C/C++ (CLI) llama-cpp-server - Inference of LLMs in pure C/C++ (server) llama-cpp-quantize - Inference of LLMs in pure C/C++ (quantize) libllama-dev - Inference of LLMs in pure C/C++ (development files) llama-cpp-dev - Inference of LLMs in pure C/C++ (common static library)

Package uploads

Upload #1

Information

Version:	0.0.4719-1
Uploaded:	2025-02-17 13:11
Source package:	llama-cpp_0.0.4719-1.dsc
Distribution:	unstable
Section:	science
Priority:	optional
Homepage:	https://github.com/ggerganov/llama.cpp

Changelog

 llama-cpp (0.0.4719-1) unstable; urgency=medium
 .
   * Update upstream

QA information

–
Package uses debhelper-compat

Debhelper compatibility level 13
–
Watch file is not present
–
Package is not native

Format: 3.0 (quilt)
–
"Maintainer" email is the same as the uploader
–
Package has lintian warnings
llama-cpp source
- W mismatched-override
  - source-is-missing [examples/server/webui/index.html] [debian/source/lintian-overrides:4]
- I debian-watch-file-is-missing
- I file-contains-fixme-placeholder
  - FIXME [debian/rules:21]
- I installable-field-mirrors-source
  - (in section for libllama) Priority [debian/control:12]
  - (in section for libllama-dev) Priority [debian/control:47]
  - (in section for llama-cpp-cli) Priority [debian/control:23]
  - (in section for llama-cpp-dev) Priority [debian/control:55]
  - (in section for llama-cpp-quantize) Priority [debian/control:39]
  - (in section for llama-cpp-server) Priority [debian/control:31]
- I missing-prerequisite-for-pyproject-backend
  - poetry.core.masonry.api (does not satisfy python3-poetry-core:any, pybuild-plugin-pyproject:any) [pyproject.toml:39]
- I out-of-date-standards-version
  - 4.5.1 (released 2020-11-17) (current is 4.7.0)
- P source-contains-prebuilt-java-object
  - [examples/llama.android/gradle/wrapper/gradle-wrapper.jar]
- P source-contains-prebuilt-javascript-object
  - [examples/server/public_legacy/index.js]
  - [examples/server/public_legacy/system-prompts.js]
- X upstream-metadata-file-is-missing
- X very-long-line-length-in-source-file
  - 1054728 > 512 [models/ggml-vocab-command-r.gguf:17831]
  - 1136 > 512 [examples/gritlm/gritlm.cpp:195]
  - 1138 > 512 [models/ggml-vocab-roberta-bpe.gguf.out:46]
  - 1198 > 512 [models/ggml-vocab-llama-spm.gguf.out:46]
  - 1198 > 512 [models/ggml-vocab-phi-3.gguf.out:46]
  - 1245 > 512 [poetry.lock:1118]
  - 1256 > 512 [examples/server/webui/src/components/Header.tsx:125]
  - 128742 > 512 [models/ggml-vocab-llama-spm.gguf:2009]
  - 129441 > 512 [models/ggml-vocab-phi-3.gguf:2063]
  - 130593 > 512 [models/ggml-vocab-bert-bge.gguf:3636]
  - 136617 > 512 [models/ggml-vocab-deepseek-coder.gguf:1886]
  - 1536 > 512 [prompts/dan-modified.txt:1]
  - 1579 > 512 [models/ggml-vocab-chameleon.gguf.out:46]
  - 1661 > 512 [prompts/dan.txt:1]
  - 1763 > 512 [examples/server/public_legacy/system-prompts.js:48]
  - 205861 > 512 [models/ggml-vocab-refact.gguf:2496]
  - 206025 > 512 [models/ggml-vocab-starcoder.gguf:2434]
  - 207776 > 512 [models/ggml-vocab-gpt-2.gguf:3658]
  - 2090 > 512 [models/templates/deepseek-ai-DeepSeek-R1-Distill-Llama-8B.jinja:1]
  - 2090 > 512 [models/templates/deepseek-ai-DeepSeek-R1-Distill-Qwen-32B.jinja:1]
  - 209930 > 512 [models/ggml-vocab-gpt-neox.gguf:3303]
  - 209930 > 512 [models/ggml-vocab-mpt.gguf:3303]
  - 23078 > 512 [examples/server/public_legacy/index.js:1]
  - 267123 > 512 [models/ggml-vocab-falcon.gguf:4587]
  - 364703 > 512 [models/ggml-vocab-baichuan.gguf:2117]
  - 4191 > 512 [tests/test-chat-template.cpp:218]
  - 467504 > 512 [models/ggml-vocab-deepseek-llm.gguf:5878]
  - 523 > 512 [examples/tts/tts-outetts.py:141]
  - 530 > 512 [docs/backend/OPENCL.md:16]
  - 534 > 512 [docs/development/token_generation_performance_tips.md:20]
  - 543375 > 512 [models/ggml-vocab-llama-bpe.gguf:7855]
  - 546 > 512 [ggml/src/ggml-kompute/kompute/README.md:511]
  - 560 > 512 [models/templates/CohereForAI-c4ai-command-r-plus-tool_use.jinja:117]
  - 575 > 512 [examples/tts/tts.cpp:534]
  - 577 > 512 [examples/llava/MobileVLM-README.md:185]
  - 584 > 512 [ggml/src/ggml-kompute/kompute/examples/pi4_mesa_build/README.md:9]
  - 585 > 512 [examples/chat-13B.bat:42]
  - 590 > 512 [examples/server/README.md:433]
  - 591 > 512 [docs/backend/CANN.md:18]
  - 621201 > 512 [models/ggml-vocab-qwen2.gguf:7400]
  - 673 > 512 [ggml/src/ggml-kompute/kompute/CODE_OF_CONDUCT.md:111]
  - 695 > 512 [examples/main/README.md:317]
  - 703 > 512 [common/json.hpp:2742]
  - 703 > 512 [examples/llama-bench/README.md:257]
  - 733 > 512 [grammars/README.md:299]
  - 736 > 512 [examples/server/public_legacy/index-new.html:860]
  - 744 > 512 [models/templates/CohereForAI-c4ai-command-r7b-12-2024-tool_use.jinja:91]
  - 790 > 512 [models/ggml-vocab-llama-bpe.gguf.out:46]
  - 795 > 512 [models/templates/meetkai-functionary-medium-v3.1.jinja:28]
  - 799 > 512 [models/ggml-vocab-deepseek-r1-qwen.gguf.out:46]
  - 799 > 512 [models/ggml-vocab-qwen2.gguf.out:46]
  - 816 > 512 [models/ggml-vocab-bert-bge.gguf.out:46]
  - 821933 > 512 [models/ggml-vocab-aquila.gguf:2933]
  - 849 > 512 [models/ggml-vocab-mpt.gguf.out:46]
  - 851 > 512 [ggml/src/ggml-vulkan/ggml-vulkan.cpp:3793]
  - 853 > 512 [models/ggml-vocab-refact.gguf.out:46]
  - 854 > 512 [models/ggml-vocab-starcoder.gguf.out:46]
  - 860 > 512 [models/ggml-vocab-command-r.gguf.out:46]
  - 870 > 512 [models/ggml-vocab-deepseek-llm.gguf.out:46]
  - 928 > 512 [models/ggml-vocab-falcon.gguf.out:46]
  - 940 > 512 [models/ggml-vocab-deepseek-coder.gguf.out:46]
  - 9726 > 512 [docs/development/llama-star/idea-arch.key:2914]
  - 982 > 512 [models/ggml-vocab-gpt-2.gguf.out:46]
- O source-is-missing
  - [examples/server/public_legacy/index-new.html]
  - [examples/server/public_legacy/index.js]
  - [examples/server/public_legacy/system-prompts.js]
–
No VCS field present
–
Package is not in Debian
–
d/copyright is in DEP5 format

Upstream Contact: https://github.com/ggerganov/llama.cpp/issues

Licenses: MIT

Comments

Hi,

Please review and rectify issue noted above.

Some work fixing ggml may also apply here.

Needs work Phil Wyett at Feb. 19, 2025, 7:37 a.m.

Upstream Contact:	https://github.com/ggerganov/llama.cpp/issues
Licenses:	MIT