summaryrefslogtreecommitdiff
path: root/ggml.h
diff options
context:
space:
mode:
authorbmwl <brian.marshall@tolko.com>2024-02-16 01:31:07 -0800
committerGitHub <noreply@github.com>2024-02-16 11:31:07 +0200
commitf486f6e1e5e9d01603d9325ab3e05f1edb362a95 (patch)
tree370aeba4b6b5f01ec2137e82484013d1be82061e /ggml.h
parent60ed04cf82dc91ade725dd7ad53f0ee81f76eccf (diff)
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>
Diffstat (limited to 'ggml.h')
-rw-r--r--ggml.h12
1 files changed, 11 insertions, 1 deletions
diff --git a/ggml.h b/ggml.h
index 01cecc1e..27001818 100644
--- a/ggml.h
+++ b/ggml.h
@@ -658,6 +658,16 @@ extern "C" {
void * wdata;
};
+ // numa strategies
+ enum ggml_numa_strategy {
+ GGML_NUMA_STRATEGY_DISABLED = 0,
+ GGML_NUMA_STRATEGY_DISTRIBUTE = 1,
+ GGML_NUMA_STRATEGY_ISOLATE = 2,
+ GGML_NUMA_STRATEGY_NUMACTL = 3,
+ GGML_NUMA_STRATEGY_MIRROR = 4,
+ GGML_NUMA_STRATEGY_COUNT
+ };
+
// misc
GGML_API void ggml_time_init(void); // call this once at the beginning of the program
@@ -668,7 +678,7 @@ extern "C" {
GGML_API void ggml_print_backtrace(void);
- GGML_API void ggml_numa_init(void); // call once for better performance on NUMA systems
+ GGML_API void ggml_numa_init(enum ggml_numa_strategy numa); // call once for better performance on NUMA systems
GGML_API bool ggml_is_numa(void); // true if init detected that system has >1 NUMA node
GGML_API void ggml_print_object (const struct ggml_object * obj);