mirror of
https://github.com/dogkeeper886/ollama37.git
synced 2025-12-15 18:27:08 +00:00
dcfb7a105c
* add build to .dockerignore * test: only build one arch * add build to .gitignore * fix ccache path * filter amdgpu targets * only filter if autodetecting * Don't clobber gpu list for default runner This ensures the GPU specific environment variables are set properly * explicitly set CXX compiler for HIP * Update build_windows.ps1 This isn't complete, but is close. Dependencies are missing, and it only builds the "default" preset. * build: add ollama subdir * add .git to .dockerignore * docs: update development.md * update build_darwin.sh * remove unused scripts * llm: add cwd and build/lib/ollama to library paths * default DYLD_LIBRARY_PATH to LD_LIBRARY_PATH in runner on macOS * add additional cmake output vars for msvc * interim edits to make server detection logic work with dll directories like lib/ollama/cuda_v12 * remove unncessary filepath.Dir, cleanup * add hardware-specific directory to path * use absolute server path * build: linux arm * cmake install targets * remove unused files * ml: visit each library path once * build: skip cpu variants on arm * build: install cpu targets * build: fix workflow * shorter names * fix rocblas install * docs: clean up development.md * consistent build dir removal in development.md * silence -Wimplicit-function-declaration build warnings in ggml-cpu * update readme * update development readme * llm: update library lookup logic now that there is one runner (#8587) * tweak development.md * update docs * add windows cuda/rocm tests --------- Co-authored-by: jmorganca <jmorganca@gmail.com> Co-authored-by: Daniel Hiltgen <daniel@ollama.com>
62 lines
1.7 KiB
C++
Vendored
62 lines
1.7 KiB
C++
Vendored
#pragma once
|
|
|
|
#include "ggml.h" // for ggml_log_level
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
#ifdef __GNUC__
|
|
#ifdef __MINGW32__
|
|
#define LLAMA_ATTRIBUTE_FORMAT(...) __attribute__((format(gnu_printf, __VA_ARGS__)))
|
|
#else
|
|
#define LLAMA_ATTRIBUTE_FORMAT(...) __attribute__((format(printf, __VA_ARGS__)))
|
|
#endif
|
|
#else
|
|
#define LLAMA_ATTRIBUTE_FORMAT(...)
|
|
#endif
|
|
|
|
//
|
|
// logging
|
|
//
|
|
|
|
LLAMA_ATTRIBUTE_FORMAT(2, 3)
|
|
void llama_log_internal (ggml_log_level level, const char * format, ...);
|
|
void llama_log_callback_default(ggml_log_level level, const char * text, void * user_data);
|
|
|
|
#define LLAMA_LOG(...) llama_log_internal(GGML_LOG_LEVEL_NONE , __VA_ARGS__)
|
|
#define LLAMA_LOG_INFO(...) llama_log_internal(GGML_LOG_LEVEL_INFO , __VA_ARGS__)
|
|
#define LLAMA_LOG_WARN(...) llama_log_internal(GGML_LOG_LEVEL_WARN , __VA_ARGS__)
|
|
#define LLAMA_LOG_ERROR(...) llama_log_internal(GGML_LOG_LEVEL_ERROR, __VA_ARGS__)
|
|
#define LLAMA_LOG_DEBUG(...) llama_log_internal(GGML_LOG_LEVEL_DEBUG, __VA_ARGS__)
|
|
#define LLAMA_LOG_CONT(...) llama_log_internal(GGML_LOG_LEVEL_CONT , __VA_ARGS__)
|
|
|
|
//
|
|
// helpers
|
|
//
|
|
|
|
template <typename T>
|
|
struct no_init {
|
|
T value;
|
|
no_init() { /* do nothing */ }
|
|
};
|
|
|
|
struct time_meas {
|
|
time_meas(int64_t & t_acc, bool disable = false);
|
|
~time_meas();
|
|
|
|
const int64_t t_start_us;
|
|
|
|
int64_t & t_acc;
|
|
};
|
|
|
|
void replace_all(std::string & s, const std::string & search, const std::string & replace);
|
|
|
|
// TODO: rename to llama_format ?
|
|
LLAMA_ATTRIBUTE_FORMAT(1, 2)
|
|
std::string format(const char * fmt, ...);
|
|
|
|
std::string llama_format_tensor_shape(const std::vector<int64_t> & ne);
|
|
std::string llama_format_tensor_shape(const struct ggml_tensor * t);
|
|
|
|
std::string gguf_kv_to_str(const struct gguf_context * ctx_gguf, int i);
|