diff options
Diffstat (limited to 'common')
| -rw-r--r-- | common/common.cpp | 6 | ||||
| -rw-r--r-- | common/common.h | 1 |
2 files changed, 7 insertions, 0 deletions
diff --git a/common/common.cpp b/common/common.cpp index e62944b9..5b3d60b3 100644 --- a/common/common.cpp +++ b/common/common.cpp @@ -993,6 +993,10 @@ bool gpt_params_find_arg(int argc, char ** argv, const std::string & arg, gpt_pa params.use_mmap = false; return true; } + if (arg == "-thp" || arg == "--transparent-huge-pages") { + params.use_thp = true; + return true; + } if (arg == "--numa") { CHECK_ARG std::string value(argv[i]); @@ -2316,6 +2320,7 @@ struct llama_model_params llama_model_params_from_gpt_params(const gpt_params & mparams.use_mlock = params.use_mlock; mparams.check_tensors = params.check_tensors; mparams.repack_tensors = params.repack_tensors; + mparams.use_thp = params.use_thp; if (params.kv_overrides.empty()) { mparams.kv_overrides = NULL; } else { @@ -3371,6 +3376,7 @@ void yaml_dump_non_result_info(FILE * stream, const gpt_params & params, const l fprintf(stream, "n_probs: %d # only used by server binary, default: 0\n", sparams.n_probs); fprintf(stream, "no_mmap: %s # default: false\n", !params.use_mmap ? "true" : "false"); fprintf(stream, "repack: %s # default: false\n", params.repack_tensors ? "true" : "false"); + fprintf(stream, "use_thp: %s # default: false\n", params.use_thp ? "true" : "false"); fprintf(stream, "penalize_nl: %s # default: false\n", sparams.penalize_nl ? "true" : "false"); fprintf(stream, "ppl_output_type: %d # default: 0\n", params.ppl_output_type); fprintf(stream, "ppl_stride: %d # default: 0\n", params.ppl_stride); diff --git a/common/common.h b/common/common.h index f6a55885..79c5fe96 100644 --- a/common/common.h +++ b/common/common.h @@ -194,6 +194,7 @@ struct gpt_params { bool warmup = true; // warmup run bool check_tensors = false; // validate tensor data bool repack_tensors = false; // repack tensors if interleaved variant is available + bool use_thp = false; // use transparent huge pages (linux only) std::string cache_type_k = "f16"; // KV cache data type for the K std::string cache_type_v = "f16"; // KV cache data type for the V |