mirror of
https://github.com/ggml-org/ggml.git
synced 2026-10-28 08:26:33 +08:00
Georgi Gerganov
da8e2a54b9
The release workflow only shows that the API/ABI check failed, but not what exactly changed, which makes failures hard to investigate. Preserve the API/ABI dumps and reports in APIABI_REPORT_DIR and upload them as a GitHub artifact, so they can be inspected after a failed run. Migrated from llama.cpp: https://github.com/ggml-org/llama.cpp/pull/30619 Assisted-by: pi:llama.cpp/ggml-org/Qwen3.8-Flash-Next-GGUF (MacBook, M5 Max, 128GB)