vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-05-17 21:20:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge commit '52e5f0a5c1' into concedo_experimental

Browse source 
# Conflicts:
#	examples/gen-docs/gen-docs.cpp
#	examples/lookup/lookup-create.cpp
#	examples/lookup/lookup-stats.cpp
#	examples/lookup/lookup.cpp
#	examples/speculative-simple/speculative-simple.cpp
#	examples/speculative/speculative.cpp
#	ggml/src/CMakeLists.txt
#	ggml/src/ggml-cann/aclnn_ops.cpp
#	ggml/src/ggml-cann/aclnn_ops.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-rpc/ggml-rpc.cpp
#	ggml/src/ggml-vulkan/ggml-vulkan.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/binary.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/get_rows.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/rms_norm_mul.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/ssm_scan.wgsl
#	tests/test-arg-parser.cpp
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-reasoning-budget.cpp
#	tools/llama-bench/llama-bench.cpp
#	tools/rpc/rpc-server.cpp
#	tools/server/webui/src/lib/components/app/chat/ChatScreen/ChatScreen.svelte
#	tools/server/webui/src/lib/components/app/chat/ChatSidebar/ChatSidebar.svelte
#	tools/server/webui/src/routes/(chat)/+page.svelte
This commit is contained in:
Concedo 2026-04-29 22:27:36 +08:00
commit 45f8ff49bb
160 changed files with 12167 additions and 8718 deletions
Download patch file Download diff file Expand all files Collapse all files

14
common/common.cpp
View file

@ -76,7 +76,7 @@ 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;
@ -191,11 +191,11 @@ 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;
@ -208,7 +208,7 @@ 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
@ -269,7 +269,7 @@ 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) {
@ -277,7 +277,7 @@ 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();
}
}
@ -1527,7 +1527,7 @@ 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