Re: llama-cpp with AMD GPUs

To: debian-ai@lists.debian.org
Subject: Re: llama-cpp with AMD GPUs
From: Christian Kastner <ckk@debian.org>
Date: Sat, 10 Feb 2024 22:39:58 +0100
Message-id: <[🔎] a08bd59a-c481-4f9c-8412-8965440b4785@debian.org>
In-reply-to: <[🔎] 30f19094-2e83-4953-97f0-abcaa2ce6333@slerp.xyz>
References: <[🔎] 39620f27-dbd1-4756-ab3d-e7464712b880@slerp.xyz> <[🔎] 24d1c8ab-62cf-4632-afc6-6a264dfbba5b@debian.org> <[🔎] 30f19094-2e83-4953-97f0-abcaa2ce6333@slerp.xyz>

On 2024-02-10 22:35, Cordell Bloor wrote:
> Opps. I meant to say "RFP". For non-technical reasons, I cannot package
> llama-cpp myself.

No problem. In that case, I'll take care of it.

Best,
Christian

Reply to:

Follow-Ups:
- Re: llama-cpp with AMD GPUs
  - From: Petter Reinholdtsen <pere@hungry.com>

References:
- llama-cpp with AMD GPUs
  - From: Cordell Bloor <cgmb@slerp.xyz>
- Re: llama-cpp with AMD GPUs
  - From: Christian Kastner <ckk@debian.org>
- Re: llama-cpp with AMD GPUs
  - From: Cordell Bloor <cgmb@slerp.xyz>

Prev by Date: Bug#1063673: ITP: llama.cpp -- Inference of Meta's LLaMA model (and others) in pure C/C++
Next by Date: Bug#1063674: RFP: llama.cpp -- Port of Facebook's LLaMA model in C/C++
Previous by thread: Re: llama-cpp with AMD GPUs
Next by thread: Re: llama-cpp with AMD GPUs
Index(es):
- Date
- Thread