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, 8 insertions, 6 deletions

diff --git a/tests/test-tokenizer-1-llama.cpp b/tests/test-tokenizer-1-llama.cpp
index a95d462c..3b2fc87a 100644
--- a/tests/test-tokenizer-1-llama.cpp
+++ b/tests/test-tokenizer-1-llama.cpp
@@ -52,18 +52,20 @@ 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());
@@ -72,7 +74,7 @@ int main(int argc, char **argv) {
         }
     }
 
-    GGML_ASSERT(llama_vocab_type(ctx) == LLAMA_VOCAB_TYPE_SPM);
+    GGML_ASSERT(llama_vocab_type(model) == LLAMA_VOCAB_TYPE_SPM);
 
 #ifdef _WIN32
     // We need this for unicode console support
@@ -80,7 +82,7 @@ int main(int argc, char **argv) {
     atexit([]() { console::cleanup(); });
 #endif
 
-    const int n_vocab = llama_n_vocab(ctx);
+    const int n_vocab = llama_n_vocab(model);
 
     for (int i = 0; i < n_vocab; ++i) {
         std::string str = llama_detokenize_spm(ctx, std::vector<int>(1, i));