mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-05-15 13:34:06 +00:00
8b7d340b6f
* ggml/hip: fix APU compatibility - soft error handling for hipMemAdviseSetCoarseGrain On AMD APU/iGPU devices (unified memory architecture), hipMemAdviseSetCoarseGrain returns hipErrorInvalidValue because the hint is not applicable to UMA systems. The previous CUDA_CHECK() call treated this as a fatal error, causing crashes on APU systems such as AMD Strix Halo (gfx1151). Fix: treat hipMemAdviseSetCoarseGrain as an optional performance hint - call it without error checking and clear any resulting error with hipGetLastError(). Also add pre-allocation debug logging (GGML_LOG_DEBUG) to help diagnose memory issues on APU systems, and store totalGlobalMem in device info. Context: AMD APUs on Windows are affected by a ROCm runtime bug that limits hipMallocManaged to ~64GB regardless of available system RAM. A fix has been submitted upstream: https://github.com/ROCm/rocm-systems/pull/4077 Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com> * ggml/hip: remove unrelated changes, keep only hipMemAdviseSetCoarseGrain fix --------- Co-authored-by: moonshadow-25 <moonshadow-25@users.noreply.github.com> Co-authored-by: Claude Sonnet 4.6 <noreply@anthropic.com>