diff options
| author | zrm <trustiosity.zrm@gmail.com> | 2023-06-26 13:57:59 -0400 |
|---|---|---|
| committer | GitHub <noreply@github.com> | 2023-06-26 20:57:59 +0300 |
| commit | b853d456018b10820686362af41b2f2f75f1eec6 (patch) | |
| tree | 264e68c8555d8509a5ac27f01eed5e6c69940174 /examples/common.h | |
| parent | 9225baef71407d799a6f7f563b77fd7f82791416 (diff) | |
ggml : add NUMA support (#1556)
* detect NUMA systems and pin work threads to nodes (linux)
* disable mmap prefetch/readahead for NUMA systems
* avoid sending finalize op to thread pool if it does nothing
* silence robot
* fix args
* make --numa a param
* recommendation that n_nodes evenly divide n_threads did not warrant such aggressive enforcement
* lower synchronization overhead
* statically allocate
* move numa state to g_state
* add description for --numa
* ggml : minor style changes
* ggml : minor style + try fix sanitizer build
* llama : allow to initialize backend with NUMA support
* llama : avoid ggml include in llama-util.h
* ggml : style / formatting
* ggml : fix handling of ops with n_threads > n_tasks > 1
* server : utilize numa parameter
---------
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
Diffstat (limited to 'examples/common.h')
| -rw-r--r-- | examples/common.h | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/examples/common.h b/examples/common.h index 71332017..9d213d6d 100644 --- a/examples/common.h +++ b/examples/common.h @@ -76,6 +76,7 @@ struct gpt_params { bool use_mmap = true; // use mmap for faster loads bool use_mlock = false; // use mlock to keep model in memory bool mem_test = false; // compute maximum memory usage + bool numa = false; // attempt optimizations that help on some NUMA systems bool export_cgraph = false; // export the computation graph bool verbose_prompt = false; // print prompt tokens before generation }; |