mirror of
https://github.com/ollama/ollama.git
synced 2026-05-23 06:01:37 -05:00
b95693056c
* feat: Bump llama.cpp to the latest master (17f7f4b) This brings in significant improvements to prefill performance for all models using the SSM_CONV and SSM_SCAN ops (granite4, jamba, falcon-h, nemotron-h, Qwen3 Next) on Apple Metal. See https://github.com/ggml-org/llama.cpp/pull/17876 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 1-4 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * fix: Update patches 5-12 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 13-18 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patch 20 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Update patches 21-31 Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> * feat: Sync vendored code The two files I'm not sure about here are the swap from gemma3-iswa.cpp to gemma3.cpp (I chose to include this because I think it's required), and the inclusion of `ggml-zendnn.h` which I chose to omit. Branch: LlamaCPPMetalSSMImprovements Signed-off-by: Gabe Goodhart <ghart@us.ibm.com> --------- Signed-off-by: Gabe Goodhart <ghart@us.ibm.com>
64 lines
1.8 KiB
C++
Vendored
64 lines
1.8 KiB
C++
Vendored
#pragma once
|
|
|
|
#include "ggml.h" // for ggml_log_level
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
#ifdef __GNUC__
|
|
# if defined(__MINGW32__) && !defined(__clang__)
|
|
# 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() = default;
|
|
};
|
|
|
|
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);
|
|
|
|
#define LLAMA_TENSOR_NAME_FATTN "__fattn__"
|