mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 27 Packages Projects Releases Wiki Activity

spec : refactor params (#22397)

Browse Source 
* spec : refactor params

* cont : fix

* cont : rename "sparam" to "sampling"

* cont : add spec params category

* cont : add info about removed arguments

* cont : skip param length check for spec params

* cont : adapt server tests
This commit is contained in:
Georgi Gerganov
2026-04-28 09:07:33 +03:00
committed by GitHub
parent 516e8d7a8a
commit 14e733e36f
18 changed files with 661 additions and 409 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/common.cpp
+7 -7
View File
@@ -70,7 +70,7 @@ common_time_meas::~common_time_meas() {
// CPU utils
//
int32_t cpu_get_num_physical_cores() {
int32_t common_cpu_get_num_physical_cores() {
#ifdef __linux__
// enumerate the set of thread siblings, num entries is num cores
std::unordered_set<std::string> siblings;
@@ -185,11 +185,11 @@ static int cpu_count_math_cpus(int n_cpu) {
/**
* Returns number of CPUs on system that are useful for math.
*/
int32_t cpu_get_num_math() {
int32_t common_cpu_get_num_math() {
#if defined(__x86_64__) && defined(__linux__) && !defined(__ANDROID__)
int n_cpu = sysconf(_SC_NPROCESSORS_ONLN);
if (n_cpu < 1) {
return cpu_get_num_physical_cores();
return common_cpu_get_num_physical_cores();
}
if (is_hybrid_cpu()) {
cpu_set_t affinity;
@@ -202,7 +202,7 @@ int32_t cpu_get_num_math() {
}
}
#endif
return cpu_get_num_physical_cores();
return common_cpu_get_num_physical_cores();
}
// Helper for setting process priority
@@ -263,7 +263,7 @@ bool set_process_priority(enum ggml_sched_priority prio) {
//
void postprocess_cpu_params(cpu_params& cpuparams, const cpu_params* role_model) {
void postprocess_cpu_params(common_cpu_params & cpuparams, const common_cpu_params * role_model) {
int32_t n_set = 0;
if (cpuparams.n_threads < 0) {
@@ -271,7 +271,7 @@ void postprocess_cpu_params(cpu_params& cpuparams, const cpu_params* role_model)
if (role_model != nullptr) {
cpuparams = *role_model;
} else {
cpuparams.n_threads = cpu_get_num_math();
cpuparams.n_threads = common_cpu_get_num_math();
}
}
@@ -1521,7 +1521,7 @@ struct llama_context_params common_context_params_to_llama(const common_params &
return cparams;
}
struct ggml_threadpool_params ggml_threadpool_params_from_cpu_params(const cpu_params & params) {
struct ggml_threadpool_params ggml_threadpool_params_from_cpu_params(const common_cpu_params & params) {
struct ggml_threadpool_params tpp;
ggml_threadpool_params_init(&tpp, params.n_threads); // setup the defaults