[bug] docker image show can't find llama backend

[Hisir0909]

LocalAI version:

v2.21.0-cublas-cuda12-ffmpeg-core(❌), v2.21.1-cublas-cuda12-core(❌), v2.19.4-cublas-cuda12-ffmpeg-core(✅) Environment, CPU architecture, OS, and Version:

Ubuntu 24.04 LTS (GNU/Linux 6.8.0-45-generic x86_64)

Describe the bug

When I use the latest two versions of the image, it prompts that the llama backend cannot be found, but it was normal in the previous versions.

To Reproduce

Pull the new image and then up. An error was found during the request; the model's YAML configuration specifies the backend as llama.

Expected behavior Like normal reasoning in version 2.19.

Logs no other

Additional context If there is any other information needed, please let me know.

[github0null]

Same here, but i found a temporary solution:

docker exec -it <your container id> /bin/bash

cp /tmp/localai/backend_data/backend-assets/grpc/llama-cpp-grpc /tmp/localai/backend_data/backend-assets/grpc/llama-cpp

[TheDarkTrumpet]

You can also change your YAML files to just do the following:

backend: llama-cpp-grpc

[mudler]

good catch, this should be fixed by https://github.com/mudler/LocalAI/pull/3789