latest-cublas-cuda12 tag does not exist on DockerHub or Quay

[roblandry]

LocalAI version:

Latest tags: quay.io/go-skynet/local-ai:latest-cublas-cuda12 or localai/localai:latest-cublas-cuda12
Version tag: quay.io/go-skynet/local-ai:v2.8.2-cublas-cuda12

Environment, CPU architecture, OS, and Version:

Linux ZEUS 6.1.64-Unraid #1 SMP PREEMPT_DYNAMIC Wed Nov 29 12:48:16 PST 2023 x86_64 Intel(R) Core(TM) i5-10400 CPU @ 2.90GHz GenuineIntel GNU/Linux

Describe the bug

"latest" tag does not exist.
I've been using Version tags.
Reading the latest docs container-images, it indicates a "latest" tag should exist.
You can validate it does not: DockerHub

To Reproduce

Update docker compose with latest tag

    image: quay.io/go-skynet/local-ai:latest-cublas-cuda12

Pull latest tag

❯ docker compose pull

Expected behavior

Tag exists and pulls

Logs

❯ docker compose pull
[+] Pulling 2/2
 ✘ api Error 
Error response from daemon: manifest for quay.io/go-skynet/local-ai:latest-cublas-cuda12 not found: manifest unknown: manifest unknown

Additional context

[nidhoggr-nil]

had the same issue, used localai/localai:master-cublas-cuda12 instead as it was there.

[roblandry]

Master is not the same as latest. Master would be more of a beta.

[phil-lipp]

It was working for v2.11, but now with the release of v2.12.X the "manifest unknown" pops up again for me

[Taikono-Himazin]

I think the problem is probably that the wrong tag name is listed in the documentation.
Probably "latest-gpu-nvidia-cuda-12" is correct.

latest-gpu-nvidia-cuda-12