Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

relocated shader compile warning

Browse Source
This commit is contained in:
LostRuins Concedo
2025-11-15 23:17:47 +08:00
parent ea22e04320
commit 86f907272a
2 changed files with 2 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files
gpttype_adapter.cpp
+1
View File
@@ -2217,6 +2217,7 @@ ModelLoadResult gpttype_load_model(const load_model_inputs inputs, FileFormat in
printf("CUDA: Set main device to %d\n",kcpp_parseinfo_maindevice);
}
printf("CUDA MMQ: %s\n",(inputs.use_mmq?"True":"False"));
printf("---\nInitializing CUDA/HIP, please wait, the following step may take a few minutes (only for first launch)...\n---\n");
ggml_cuda_set_mul_mat_q(inputs.use_mmq);
#endif
if((file_format_meta.model_architecture == GGUFArch::ARCH_QWEN2 || file_format_meta.model_architecture == GGUFArch::ARCH_QWEN2VL) && !kcpp_data->flash_attn)