When I use the docker images, I get a platform mismatch what am I missing? #11462
Replies: 2 comments 1 reply
-
This should be fixed now. |
Beta Was this translation helpful? Give feedback.
1 reply
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
When I run the following on my ubuntu 24 install on Hetzner, I'm getting the following error.
docker run -d --name llamacpp -v /opt/llamacpp/models:/root/.cache/llama.cpp -p 8000:8000 ghcr.io/ggerganov/llama.cpp:full --hf-repo unsloth/DeepSeek-R1-Distill-Qwen-1.5B-GGUF --hf-file DeepSeek-R1-Distill-Qwen-1.5B-Q4_K_M.gguf --ctx-size 2048 --port 8000 --api-key genaiisspendy --host 0.0.0.0
Results in...
WARNING: The requested image's platform (linux/arm64) does not match the detected host platform (linux/amd64/v3) and no specific platform was requested 352f6478d5bf83d8991a8fdb3b9ac1eaa5485f5a59f796a1104f0646725ddb50
I looked at the docs on the docker page and I'm not seeing anything that is standing out https://github.com/ggerganov/llama.cpp/blob/master/docs/docker.md
I looked at the past issues this week and I'm coming up short.
This issue pointed me to past build that works but it doesn't wokr for Deepseek. #11304
If I can make the server instead that's cool, I'm just not sure how.
If there's some workaround I'm all for that too.
System details;
OS: Ubuntu 24.04 noble
Kernel: x86_64 Linux 6.8.0-51-generic
Shell: bash 5.2.21
Disk: 5.4G / 151G (4%)
CPU: AMD EPYC @ 4x 2.445GHz
GPU: Red Hat, Inc. Virtio 1.0 GPU (rev 01)
Beta Was this translation helpful? Give feedback.
All reactions