Command line switch to use F16 for memory_k and memory_v (refactor of #154) (#294)

* Use F16 for memory_k and memory_v

* add command line switch to use f16 instead of f32 for memory k+v

---------

Co-authored-by: Ty Everett <ty@tyweb.us>

1 files changed, 3 insertions, 0 deletions

diff --git a/utils.cpp b/utils.cpp
index 320d7c3..99cb30b 100644
--- a/utils.cpp
+++ b/utils.cpp
@@ -49,6 +49,8 @@ bool gpt_params_parse(int argc, char ** argv, gpt_params & params) {
             params.top_k = std::stoi(argv[++i]);
         } else if (arg == "-c" || arg == "--ctx_size") {
             params.n_ctx = std::stoi(argv[++i]);
+        } else if (arg == "--memory_f16") {
+            params.memory_f16 = true;
         } else if (arg == "--top_p") {
             params.top_p = std::stof(argv[++i]);
         } else if (arg == "--temp") {
@@ -104,6 +106,7 @@ void gpt_print_usage(int /*argc*/, char ** argv, const gpt_params & params) {
     fprintf(stderr, "  --repeat_last_n N     last n tokens to consider for penalize (default: %d)\n", params.repeat_last_n);
     fprintf(stderr, "  --repeat_penalty N    penalize repeat sequence of tokens (default: %.1f)\n", params.repeat_penalty);
     fprintf(stderr, "  -c N, --ctx_size N    size of the prompt context (default: %d)\n", params.n_ctx);
+    fprintf(stderr, "  --memory_f16          use f16 instead of f32 for memory key+value\n");
     fprintf(stderr, "  --temp N              temperature (default: %.1f)\n", params.temp);
     fprintf(stderr, "  -b N, --batch_size N  batch size for prompt processing (default: %d)\n", params.n_batch);
     fprintf(stderr, "  -m FNAME, --model FNAME\n");