Open nivibilla opened 4 days ago
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)
GGML_ASSERT: ggml.c:21763: svcntb() == QK8_0
version: 3220 (f702a90e) built with clang version 18.1.7 for aarch64-unknown-linux-android28
Other? (Please let us know in description)
./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```
Seems to be an issue caused by the SVE integration PR
it works fine after testing with an older release before that PR.
What happened?
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