Skip to content

arg : bring back missing ifdef #9411

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Sep 10, 2024
Merged

arg : bring back missing ifdef #9411

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
cae7e22
arg : bring back missing ifdef
ngxson Sep 10, 2024
246a088
replace with llama_supports_gpu_offload
ngxson Sep 10, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
28 changes: 13 additions & 15 deletions common/arg.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1422,20 +1422,18 @@ gpt_params_context gpt_params_parser_init(gpt_params & params, llama_example ex,
params.split_mode = LLAMA_SPLIT_MODE_NONE;
} else if (arg_next == "layer") {
params.split_mode = LLAMA_SPLIT_MODE_LAYER;
}
else if (arg_next == "row") {
} else if (arg_next == "row") {
#ifdef GGML_USE_SYCL
fprintf(stderr, "warning: The split mode value:[row] is not supported by llama.cpp with SYCL. It's developing.\nExit!\n");
exit(1);
#endif // GGML_USE_SYCL
params.split_mode = LLAMA_SPLIT_MODE_ROW;
}
else {
} else {
throw std::invalid_argument("invalid value");
}
#ifndef GGML_USE_CUDA_SYCL_VULKAN
fprintf(stderr, "warning: llama.cpp was compiled without CUDA/SYCL/Vulkan. Setting the split mode has no effect.\n");
#endif // GGML_USE_CUDA_SYCL_VULKAN
if (!llama_supports_gpu_offload()) {
fprintf(stderr, "warning: llama.cpp was compiled without support for GPU offload. Setting the split mode has no effect.\n");
}
}
));
add_opt(llama_arg(
Expand All @@ -1455,24 +1453,24 @@ gpt_params_context gpt_params_parser_init(gpt_params & params, llama_example ex,
}
for (size_t i = 0; i < llama_max_devices(); ++i) {
if (i < split_arg.size()) {
params.tensor_split[i] = std::stof(split_arg[i]);
params.tensor_split[i] = std::stof(split_arg[i]);
} else {
params.tensor_split[i] = 0.0f;
params.tensor_split[i] = 0.0f;
}
}
#ifndef GGML_USE_CUDA_SYCL_VULKAN
fprintf(stderr, "warning: llama.cpp was compiled without CUDA/SYCL/Vulkan. Setting a tensor split has no effect.\n");
#endif // GGML_USE_CUDA_SYCL_VULKAN
if (!llama_supports_gpu_offload()) {
fprintf(stderr, "warning: llama.cpp was compiled without support for GPU offload. Setting a tensor split has no effect.\n");
}
}
));
add_opt(llama_arg(
{"-mg", "--main-gpu"}, "INDEX",
format("the GPU to use for the model (with split-mode = none), or for intermediate results and KV (with split-mode = row) (default: %d)", params.main_gpu),
[](gpt_params & params, int value) {
params.main_gpu = value;
#ifndef GGML_USE_CUDA_SYCL_VULKAN
fprintf(stderr, "warning: llama.cpp was compiled without CUDA/SYCL/Vulkan. Setting the main GPU has no effect.\n");
#endif // GGML_USE_CUDA_SYCL_VULKAN
if (!llama_supports_gpu_offload()) {
fprintf(stderr, "warning: llama.cpp was compiled without support for GPU offload. Setting the main GPU has no effect.\n");
}
}
));
add_opt(llama_arg(
Expand Down
8 changes: 0 additions & 8 deletions common/common.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,14 +56,6 @@
#pragma warning(disable: 4244 4267) // possible loss of data
#endif

#if (defined(GGML_USE_CUDA) || defined(GGML_USE_SYCL))
#define GGML_USE_CUDA_SYCL
#endif

#if (defined(GGML_USE_CUDA) || defined(GGML_USE_SYCL)) || defined(GGML_USE_VULKAN)
#define GGML_USE_CUDA_SYCL_VULKAN
#endif

#if defined(LLAMA_USE_CURL)
#ifdef __linux__
#include <linux/limits.h>
Expand Down
Loading