vrr/prima.cpp
2
0
Fork 0
mirror of https://github.com/Lizonghang/prima.cpp.git synced 2025-09-10 06:54:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix auto schedule logic

Browse source
This commit is contained in:
Lizonghang 2025-01-29 13:13:37 +04:00
parent e7c6b830e6
commit 849b47ccd0
2 changed files with 3 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
src/llama.cpp
View file

@ -3618,6 +3618,7 @@ void llama_profile_device(
dev_info->cpu_props.name = cpu_props.name;
dev_info->cpu_props.description = cpu_props.description;
#if defined(GGML_USE_METAL) || defined(GGML_USE_CUDA)
dev_info->gpu_props.name = gpu_props.name;
dev_info->gpu_props.description = gpu_props.description;
@ -3630,6 +3631,7 @@ void llama_profile_device(
dev_info->gpu_props.cuda_read_vram_bw = device_cuda_read_vram_bw();
dev_info->gpu_props.metal_mem_cpy_delay = device_metal_mem_copy(model);
dev_info->gpu_props.cuda_mem_cpy_delay = device_cuda_mem_copy(model);
#endif
if (is_dtype_exist(n_params, GGML_TYPE_F32)) {
dev_info->cpu_props.flops_f32_f32 = device_cpu_flops (model, GGML_TYPE_F32, GGML_TYPE_F32, n_threads);