furyhawk/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-21 02:05:51 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cuda : restore prop.integrated on HIP builds (#24233)

Browse Source 
PR #16308 set info.devices[id].integrated = false unconditionally for all
CUDA/HIP devices as a workaround for corrupted output on Jetson Orin
(#15034). On HIP/ROCm the device's real hipDeviceProp_t.integrated flag is
needed: with the cached field forced to false, supports_buft() refuses
CUDA host buffers on AMD APU/UMA parts, while get_type() already reads
prop.integrated (#23007) — an inconsistency that breaks integrated-GPU
host-buffer use on ROCm.

Guard the workaround so it only applies to non-HIP (CUDA) builds and
restore prop.integrated for HIP, keeping the Jetson workaround intact for
CUDA.

Fixes #23977

Signed-off-by: liminfei-amd <91481003+liminfei-amd@users.noreply.github.com>
This commit is contained in:
liminfei-amd
2026-07-16 11:10:08 +02:00
committed by GitHub
parent 5839ba3524
commit c7d8722922
1 changed files with 4 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cuda/ggml-cuda.cu
+4
View File
@@ -248,7 +248,11 @@ static ggml_cuda_device_info ggml_cuda_init() {
info.default_tensor_split[id] = total_vram;
total_vram += prop.totalGlobalMem;
#if defined(GGML_USE_HIP)
info.devices[id].integrated = prop.integrated;
#else
info.devices[id].integrated = false; // Temporarily disabled due to issues with corrupted output (e.g. #15034)
#endif
info.devices[id].nsm = prop.multiProcessorCount;
info.devices[id].smpb = prop.sharedMemPerBlock;
info.devices[id].warp_size = prop.warpSize;