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, 9 insertions, 8 deletions

diff --git a/examples/quantize-stats/quantize-stats.cpp b/examples/quantize-stats/quantize-stats.cpp
index 94edb94d..dd76b1ce 100644
--- a/examples/quantize-stats/quantize-stats.cpp
+++ b/examples/quantize-stats/quantize-stats.cpp
@@ -309,21 +309,22 @@ int main(int argc, char ** argv) {
     llama_context * ctx;
 
     {
-        auto lparams = llama_context_default_params();
+        auto mparams = llama_model_default_params();
+        mparams.use_mlock  = false;
 
-        lparams.n_ctx      = 256;
-        lparams.seed       = 1;
-        lparams.f16_kv     = false;
-        lparams.use_mlock  = false;
-
-        model = llama_load_model_from_file(params.model.c_str(), lparams);
+        model = llama_load_model_from_file(params.model.c_str(), mparams);
 
         if (model == NULL) {
             fprintf(stderr, "%s: error: failed to load model '%s'\n", __func__, params.model.c_str());
             return 1;
         }
 
-        ctx = llama_new_context_with_model(model, lparams);
+        auto cparams = llama_context_default_params();
+        cparams.n_ctx      = 256;
+        cparams.seed       = 1;
+        cparams.f16_kv     = false;
+
+        ctx = llama_new_context_with_model(model, cparams);
 
         if (ctx == NULL) {
             fprintf(stderr, "%s: error: failed to create context with model '%s'\n", __func__, params.model.c_str());