mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2024-10-31 23:28:51 +01:00
f486f6e1e5
* 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> |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| README.md | ||
| simple.cpp | ||
llama.cpp/example/simple
The purpose of this example is to demonstrate a minimal usage of llama.cpp for generating text with a given prompt.
./simple ./models/llama-7b-v2/ggml-model-f16.gguf "Hello my name is"
...
main: n_len = 32, n_ctx = 2048, n_parallel = 1, n_kv_req = 32
Hello my name is Shawn and I'm a 20 year old male from the United States. I'm a 20 year old
main: decoded 27 tokens in 2.31 s, speed: 11.68 t/s
llama_print_timings: load time = 579.15 ms
llama_print_timings: sample time = 0.72 ms / 28 runs ( 0.03 ms per token, 38888.89 tokens per second)
llama_print_timings: prompt eval time = 655.63 ms / 10 tokens ( 65.56 ms per token, 15.25 tokens per second)
llama_print_timings: eval time = 2180.97 ms / 27 runs ( 80.78 ms per token, 12.38 tokens per second)
llama_print_timings: total time = 2891.13 ms