llama.cpp : split llama_context_params into model and context params (#3301)

* llama.cpp : split llama_context_params into model and context params

ggml-ci

* fix metal build

* fix freq_base/scale default to model value

* llama-bench : keep the same model between tests when possible

* move n_threads to llama_context_params, add n_threads_batch

* fix mpi build

* remove kv_size(), cuda scratch fixes

* remove low-vram option

* add n_threads_batch to system info, refactor to get_system_info()

* add documentation about --threads-batch to the READMEs

* llama-bench fix

* main : fix rope freq/scale warning

* llama.cpp : add llama_get_model
common : add llama_tokenize from model

* remove duplicated ctx/model functions

ggml-ci

* cuda : print total VRAM used

1 files changed, 7 insertions, 5 deletions

diff --git a/tests/test-tokenizer-0-falcon.cpp b/tests/test-tokenizer-0-falcon.cpp
index 836fb8ad..d51851e2 100644
--- a/tests/test-tokenizer-0-falcon.cpp
+++ b/tests/test-tokenizer-0-falcon.cpp
@@ -62,18 +62,20 @@ int main(int argc, char **argv) {
 
     // load the vocab
     {
-        auto lparams = llama_context_default_params();
+        auto mparams = llama_model_default_params();
 
-        lparams.vocab_only = true;
+        mparams.vocab_only = true;
 
-        model = llama_load_model_from_file(fname.c_str(), lparams);
+        model = llama_load_model_from_file(fname.c_str(), mparams);
 
         if (model == NULL) {
             fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
             return 1;
         }
 
-        ctx = llama_new_context_with_model(model, lparams);
+        auto cparams = llama_context_default_params();
+
+        ctx = llama_new_context_with_model(model, cparams);
 
         if (ctx == NULL) {
             fprintf(stderr, "%s: error: failed to load vocab '%s'\n", __func__, fname.c_str());
@@ -82,7 +84,7 @@ int main(int argc, char **argv) {
         }
     }
 
-    if (llama_vocab_type(ctx) != LLAMA_VOCAB_TYPE_BPE) {
+    if (llama_vocab_type(model) != LLAMA_VOCAB_TYPE_BPE) {
         fprintf(stderr, "%s : error: vocab type is not SPM\n", __func__);
         llama_free_model(model);
         llama_free(ctx);