ggerganov / llama.cpp

LLM inference in C/C++
MIT License
60.95k stars 8.7k forks source link

Bug: abort on Android (pixel 8 pro) #8109

Open nivibilla opened 4 days ago

nivibilla commented 4 days ago

What happened?

Screenshot_20240625-122328

Getting GGML_ASSERT: ggml.c:21763: svcntb() == QK8_0 when trying to build and run llama.cpp with llama 3 8b q4 on Android (pixel 8 pro)

Name and Version

version: 3220 (f702a90e) built with clang version 18.1.7 for aarch64-unknown-linux-android28

What operating system are you seeing the problem on?

Other? (Please let us know in description)

Relevant log output

./llama-server -m ./models/Meta-Llama-3-8B-Instruct.Q4_K_M.gguf --chat-template llama3 --no-mmap
INFO [                    main] build info | tid="542774631704" timestamp=1719314594 build=3220 commit="f702a90e"
GGML_ASSERT: ggml.c:21763: svcntb() == QK8_0
Aborted```
nivibilla commented 3 days ago

Seems to be an issue caused by the SVE integration PR

it works fine after testing with an older release before that PR.