vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

allocators wip

Browse source 
renamed ggml_backend functions
changed ggml_buffer and ggml_backend to always be used as pointers
rename ggml_tensor::params -> op_params
This commit is contained in:
slaren 2023-07-17 19:03:51 +02:00
parent 1102ff56db
commit 295f85654a
8 changed files with 640 additions and 365 deletions
Download patch file Download diff file Expand all files Collapse all files

18
examples/common.cpp
View file

@ -327,24 +327,24 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
params.n_gpu_layers = std::stoi(argv[i]);
#else
fprintf(stderr, "warning: not compiled with GPU offload support, --n-gpu-layers option will be ignored\n");
fprintf(stderr, "warning: see main README.md for information on enabling GPU BLAS support\n");
fprintf(stderr, "warning: see main README.md for information on enabling GPU support\n");
#endif
} else if (arg == "--main-gpu" || arg == "-mg") {
if (++i >= argc) {
invalid_param = true;
break;
}
#ifdef GGML_USE_CUBLAS
#ifdef GGML_USE_CUDA
params.main_gpu = std::stoi(argv[i]);
#else
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. It is not possible to set a main GPU.\n");
fprintf(stderr, "warning: llama.cpp was compiled without CUDA. It is not possible to set a main GPU.\n");
#endif
} else if (arg == "--tensor-split" || arg == "-ts") {
if (++i >= argc) {
invalid_param = true;
break;
}
#ifdef GGML_USE_CUBLAS
#ifdef GGML_USE_CUDA
std::string arg_next = argv[i];
// split string by , and /
@ -361,14 +361,14 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
}
}
#else
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. It is not possible to set a tensor split.\n");
#endif // GGML_USE_CUBLAS
fprintf(stderr, "warning: llama.cpp was compiled without CUDA. It is not possible to set a tensor split.\n");
#endif // GGML_USE_CUDA
} else if (arg == "--low-vram" || arg == "-lv") {
#ifdef GGML_USE_CUBLAS
#ifdef GGML_USE_CUDA
params.low_vram = true;
#else
fprintf(stderr, "warning: llama.cpp was compiled without cuBLAS. It is not possible to set lower vram usage.\n");
#endif // GGML_USE_CUBLAS
fprintf(stderr, "warning: llama.cpp was compiled without CUDA. It is not possible to set lower vram usage.\n");
#endif // GGML_USE_CUDA
} else if (arg == "--no-mmap") {
params.use_mmap = false;
} else if (arg == "--mtest") {