vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-08 09:59:50 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 3

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

2
ggml/src/ggml-cuda/ggml-cuda.cu
View file

@ -208,7 +208,7 @@ static ggml_cuda_device_info ggml_cuda_init() {
//#else
// GGML_LOG_INFO("%s: GGML_CUDA_FORCE_CUBLAS: no\n", __func__);
//#endif // GGML_CUDA_FORCE_CUBLAS
GGML_LOG_INFO("---\nInitializing CUDA/HIP, please wait, the following step may take a few minutes (only for first launch)...\n---\n");
GGML_LOG_INFO("%s: found %d " GGML_CUDA_NAME " devices:\n", __func__, info.device_count);
std::vector<std::pair<int, std::string>> turing_devices_without_mma;

1
gpttype_adapter.cpp
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)