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

To: Christian Kastner <ckk@debian.org>, 1063673@bugs.debian.org
Subject: Bug#1063673: ITP: llama.cpp -- Inference of Meta's LLaMA model (and others) in pure C/C++
From: Petter Reinholdtsen <pere@hungry.com>
Date: Tue, 13 Feb 2024 08:36:30 +0100
Message-id: <[🔎] sa6mss4bytd.fsf@hjemme.reinholdtsen.name>
Reply-to: Petter Reinholdtsen <pere@hungry.com>, 1063673@bugs.debian.org
In-reply-to: <[🔎] d373f55c-2869-490b-aeaf-0fba8c10c02e@debian.org>
References: <[🔎] d373f55c-2869-490b-aeaf-0fba8c10c02e@debian.org> <[🔎] d373f55c-2869-490b-aeaf-0fba8c10c02e@debian.org>

I tried building the CPU edition on one machine and run it on another,
and experienced illegal instruction exceptions.  I suspect this mean one
need to be careful when selecting build profile to ensure it work on all
supported Debian platforms.

I would be happy to help getting this up and running.  Please let me
know when you have published a git repo with the packaging rules.

-- 
Happy hacking
Petter Reinholdtsen

Reply to:

Follow-Ups:
- Bug#1063673: ITP: llama.cpp -- Inference of Meta's LLaMA model (and others) in pure C/C++
  - From: Christian Kastner <ckk@debian.org>

References:
- Bug#1063673: ITP: llama.cpp -- Inference of Meta's LLaMA model (and others) in pure C/C++
  - From: Christian Kastner <ckk@debian.org>

Prev by Date: Bug#1063829: ITP: tftp-proxy -- proxy to redirect TFTP requests to HTTP
Next by Date: Bug#1063094: marked as done (ITP: python-rtf-tokenize -- Simple RTF tokenizer for python)
Previous by thread: Bug#1063673: ITP: llama.cpp -- Inference of Meta's LLaMA model (and others) in pure C/C++
Next by thread: Bug#1063673: ITP: llama.cpp -- Inference of Meta's LLaMA model (and others) in pure C/C++
Index(es):
- Date
- Thread