tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-11 11:05:39 -04:00
Code Issues Packages Projects Releases Wiki Activity

HIP: Prepare reduction operators for wave 64

Browse Source
This commit is contained in:
uvos
2025-01-29 19:12:42 +01:00
parent c300e68ef4
commit 6af1ca48cb
2 changed files with 28 additions and 35 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ggml/src/ggml-cuda/ggml-cuda.cu
View File

@@ -240,8 +240,8 @@ static ggml_cuda_device_info ggml_cuda_init() {
info.default_tensor_split[id] = total_vram;
total_vram += prop.totalGlobalMem;
info.devices[id].nsm = prop.multiProcessorCount;
info.devices[id].smpb = prop.sharedMemPerBlock;
info.devices[id].nsm = prop.multiProcessorCount;
info.devices[id].smpb = prop.sharedMemPerBlock;
info.devices[id].warp_size = prop.warpSize;
#if defined(GGML_USE_HIP) && defined(__HIP_PLATFORM_AMD__)
info.devices[id].smpbo = prop.sharedMemPerBlock;