ggml : add numa options (#5377)

* Added numa options to allow finer grained control as well as plumbing for a new mirror mode that will require numa.h

* Reverted Makefile

* Fixed include

* Removed sched.h from ggml.h, moved ggml_get_numa_affinity into ggml.c, removed trailing whitespace and fixed up a few inconsistent variables

* removed trailing whitespace

* Added numa options to allow finer grained control as well as plumbing for a new mirror mode that will require numa.h

* Reverting Makefile

* Fixed a number of issues with the move from BOOL to ggml_numa_strategies. Added a note about mirror mode note being implemented yet

* Removing MIRROR_MODE code for this PR

* Removing last bit of MIRROR_MODE code for this PR

* Removing unneeded branch in server.cpp example and moving get_numa_affinity and making it static

* Fixed lingering init_llama_backend() bool calls in tests and examples

* Remote enum llama_numa_strategies

* Revert bad merge with dynatemp flags

* add missing enum ggml_numa_strategies declaration and revert sync problem with master

* add missing enum ggml_numa_strategies declaration

* fixed ggml_init_numa variable

* Update ggml.h

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* Update READMEs with info about numa flags, change INTERLEAVE strategy name to DISTRIBUTE everywhere, implement the improved distribution strategy from @rankaiyx, fix a spelling mistake and un-merge some bad merges

* split numa init out from llama_backend_init and created llama_numa_init. Updated all code paths and samples

* Fix up some boolean vs enum comparisons

* Added #ifdefs for non-Linux OS that don't have cpu_set_t datatype

* Update ggml.h

Align enum values

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update ggml.c

Remove whitespace

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update ggml.c

align paremeters

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update examples/server/server.cpp

remove whitespace and align brace

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Update common/common.cpp

Remove whitespace and align brace

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* unified ggml_numa_strategy enum and fixed text alignment in server.cpp example

* Update ggml.c

simplified return for platforms without NUMA support

Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>

* removed redundant else from cli argument processing of --numa

* whitespace

---------

Co-authored-by: root <root@nenya.lothlorien.ca>
Co-authored-by: Jared Van Bortel <cebtenzzre@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Co-authored-by: Jared Van Bortel <jared@nomic.ai>

6 files changed, 6 insertions, 6 deletions

diff --git a/tests/test-autorelease.cpp b/tests/test-autorelease.cpp
index 36a23c0b..57fa0001 100644
--- a/tests/test-autorelease.cpp
+++ b/tests/test-autorelease.cpp
@@ -12,7 +12,7 @@ int main(int argc, char ** argv) {
     auto * model_path = get_model_or_exit(argc, argv);
 
     std::thread([&model_path]() {
-        llama_backend_init(false);
+        llama_backend_init();
         auto * model = llama_load_model_from_file(model_path, llama_model_default_params());
         auto * ctx = llama_new_context_with_model(model, llama_context_default_params());
         llama_free(ctx);
diff --git a/tests/test-model-load-cancel.cpp b/tests/test-model-load-cancel.cpp
index 7ea4bbac..858535c3 100644
--- a/tests/test-model-load-cancel.cpp
+++ b/tests/test-model-load-cancel.cpp
@@ -14,7 +14,7 @@ int main(int argc, char *argv[] ) {
     fprintf(stderr, "using '%s'\n", model_path);
     fclose(file);
 
-    llama_backend_init(false);
+    llama_backend_init();
     auto params = llama_model_params{};
     params.use_mmap = false;
     params.progress_callback = [](float progress, void * ctx){
diff --git a/tests/test-tokenizer-0-falcon.cpp b/tests/test-tokenizer-0-falcon.cpp
index a4e9d2b9..472b0b3a 100644
--- a/tests/test-tokenizer-0-falcon.cpp
+++ b/tests/test-tokenizer-0-falcon.cpp
@@ -61,7 +61,7 @@ int main(int argc, char **argv) {
     llama_model * model;
     llama_context * ctx;
 
-    llama_backend_init(false);
+    llama_backend_init();
 
     // load the vocab
     {
diff --git a/tests/test-tokenizer-0-llama.cpp b/tests/test-tokenizer-0-llama.cpp
index 39c8d188..0a16cd7e 100644
--- a/tests/test-tokenizer-0-llama.cpp
+++ b/tests/test-tokenizer-0-llama.cpp
@@ -60,7 +60,7 @@ int main(int argc, char **argv) {
     llama_model * model;
     llama_context * ctx;
 
-    llama_backend_init(false);
+    llama_backend_init();
 
     // load the vocab
     {
diff --git a/tests/test-tokenizer-1-bpe.cpp b/tests/test-tokenizer-1-bpe.cpp
index 3bb62956..3596ce55 100644
--- a/tests/test-tokenizer-1-bpe.cpp
+++ b/tests/test-tokenizer-1-bpe.cpp
@@ -25,7 +25,7 @@ int main(int argc, char **argv) {
     llama_model * model;
     llama_context * ctx;
 
-    llama_backend_init(false);
+    llama_backend_init();
 
     // load the vocab
     {
diff --git a/tests/test-tokenizer-1-llama.cpp b/tests/test-tokenizer-1-llama.cpp
index b0d814a4..9333f868 100644
--- a/tests/test-tokenizer-1-llama.cpp
+++ b/tests/test-tokenizer-1-llama.cpp
@@ -25,7 +25,7 @@ int main(int argc, char **argv) {
     llama_model * model;
     llama_context * ctx;
 
-    llama_backend_init(false);
+    llama_backend_init();
 
     // load the vocab
     {