[Date Prev][Date Next] [Thread Prev][Thread Next] [Date Index] [Thread Index]

Bug#1063673: marked as done (ITP: llama.cpp -- Inference of Meta's LLaMA model (and others) in pure C/C++)

Your message dated Mon, 21 Apr 2025 09:25:49 +0200
with message-id <sa68qnu6kn6.fsf@hjemme.reinholdtsen.name>
and subject line [Debian FTP Masters] Accepted llama.cpp 5151+dfsg-1~exp2 (source amd64) into experimental
has caused the Debian Bug report #1063673,
regarding ITP: llama.cpp -- Inference of Meta's LLaMA model (and others) in pure C/C++
to be marked as done.

This means that you claim that the problem has been dealt with.
If this is not the case it is now your responsibility to reopen the
Bug report if necessary, and/or fix the problem forthwith.

(NB: If you are a system administrator and have no idea what this
message is talking about, this may indicate a serious mail system
misconfiguration somewhere. Please contact owner@bugs.debian.org
immediately.)


-- 
1063673: https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=1063673
Debian Bug Tracking System
Contact owner@bugs.debian.org with problems
--- Begin Message --- 
Package: wnpp
Severity: wishlist
Owner: Christian Kastner <ckk@debian.org>
X-Debbugs-Cc: debian-devel@lists.debian.org, debian-ai@lists.debian.org

* Package name    : llama.cpp
  Version         : b2116
  Upstream Author : Georgi Gerganov
* URL             : https://github.com/ggerganov/llama.cpp
* License         : MIT
  Programming Lang: C++
  Description     : Inference of Meta's LLaMA model (and others) in pure C/C++

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.

* Plain C/C++ implementation without any dependencies
* Apple silicon is a first-class citizen - optimized via ARM NEON,
  Accelerate and Metal frameworks
* AVX, AVX2 and AVX512 support for x86 architectures
* 2-bit, 3-bit, 4-bit, 5-bit, 6-bit, and 8-bit integer quantization for
  faster inference and reduced memory use
* Custom CUDA kernels for running LLMs on NVIDIA GPUs (support for AMD
  GPUs via HIP)
* Vulkan, SYCL, and (partial) OpenCL backend support
* CPU+GPU hybrid inference to partially accelerate models larger than
  the total VRAM capacity

This package will be maintained by the Debian Deep Learning Team.

--- End Message ---
--- Begin Message --- 
Version: 5151+dfsg-1~exp2

-------------------- Start of forwarded message --------------------
From: Debian FTP Masters <ftpmaster@ftp-master.debian.org>
To: debian-devel-changes@lists.debian.org,
 debian-experimental-changes@lists.debian.org
Subject: Accepted llama.cpp 5151+dfsg-1~exp2 (source amd64) into experimental
Date: Sun, 20 Apr 2025 09:00:13 +0000


-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA512

Format: 1.8
Date: Fri, 18 Apr 2025 12:40:36 +0200
Source: llama.cpp
Binary: llama.cpp llama.cpp-dbgsym
Architecture: source amd64
Version: 5151+dfsg-1~exp2
Distribution: experimental
Urgency: medium
Maintainer: Debian Deep Learning Team <debian-ai@lists.debian.org>
Changed-By: Christian Kastner <ckk@debian.org>
Description:
 llama.cpp  - LLM inference in C/C++
Closes: 1063763
Changes:
 llama.cpp (5151+dfsg-1~exp2) experimental; urgency=medium
 .
   * Initial release (Closes: #1063763)
Checksums-Sha1:
 448e523264ed4400e163a9e697fc6c84e4ac1ba7 2051 llama.cpp_5151+dfsg-1~exp2.dsc
 68e227f09d6911cf4dbdfd9959af049eca3b9deb 4152836 llama.cpp_5151+dfsg.orig.tar.xz
 6f37bdd03ba6428b197945c2f1b2bf92c36b6ae3 6888 llama.cpp_5151+dfsg-1~exp2.debian.tar.xz
 03d6d31c726d183b95b157a19208b79087a911bc 244383044 llama.cpp-dbgsym_5151+dfsg-1~exp2_amd64.deb
 76936903c90fe6b36bf2e852a45ee8dc0665fba3 8113 llama.cpp_5151+dfsg-1~exp2_amd64.buildinfo
 1aa668e69ce056747397335db0c56e027375e173 5975280 llama.cpp_5151+dfsg-1~exp2_amd64.deb
Checksums-Sha256:
 d1c665fb67fd33669d416a24f9ae374941201c5dfd19dce73ebaf8d1a03001e1 2051 llama.cpp_5151+dfsg-1~exp2.dsc
 3691c7be280f82f29769a00bdcf28d2d918273dc2692f1847a8eb32ebc9182b7 4152836 llama.cpp_5151+dfsg.orig.tar.xz
 e64e0a674df320dfff53d3b35627ca3896156d784b1908705ae84eee32b32ecd 6888 llama.cpp_5151+dfsg-1~exp2.debian.tar.xz
 9e52b9355a327039e98fb4debf826e2205563372c675ede752cb0d499ae5b43a 244383044 llama.cpp-dbgsym_5151+dfsg-1~exp2_amd64.deb
 106a62125b098b80d0ae48f035b0d85984373f45944ccf2ef03bc616eaeed551 8113 llama.cpp_5151+dfsg-1~exp2_amd64.buildinfo
 34b595f14108217913f66a85ab622c78f8c12b9bfa5521d3220746dad88239de 5975280 llama.cpp_5151+dfsg-1~exp2_amd64.deb
Files:
 fcbe50e47b41ff236588fc4ceab7188f 2051 science optional llama.cpp_5151+dfsg-1~exp2.dsc
 d879483dbb620a5e21e8f71c7f8e7d10 4152836 science optional llama.cpp_5151+dfsg.orig.tar.xz
 03537dd3653cad84b58ab8a06d50b764 6888 science optional llama.cpp_5151+dfsg-1~exp2.debian.tar.xz
 0af0586103c7058ea65eab1e75bc879e 244383044 debug optional llama.cpp-dbgsym_5151+dfsg-1~exp2_amd64.deb
 41991a3d19400dabe9c1836adb984d43 8113 science optional llama.cpp_5151+dfsg-1~exp2_amd64.buildinfo
 d86b3605346b5c84de1163ba6f9e10ac 5975280 science optional llama.cpp_5151+dfsg-1~exp2_amd64.deb

-----BEGIN PGP SIGNATURE-----
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=/gcs
-----END PGP SIGNATURE-----

Attachment: pgpWgK9zf0YkC.pgp
Description: PGP signature

-------------------- End of forwarded message --------------------

--- End Message ---
Reply to: