From 16bc66d9479edd5ee12ec734973554d4493c5dfa Mon Sep 17 00:00:00 2001 From: slaren Date: Thu, 28 Sep 2023 21:42:38 +0200 Subject: 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 --- examples/embd-input/embd-input-test.cpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'examples/embd-input/embd-input-test.cpp') diff --git a/examples/embd-input/embd-input-test.cpp b/examples/embd-input/embd-input-test.cpp index e5e040f6..dc4a0e48 100644 --- a/examples/embd-input/embd-input-test.cpp +++ b/examples/embd-input/embd-input-test.cpp @@ -8,7 +8,7 @@ int main(int argc, char** argv) { auto mymodel = create_mymodel(argc, argv); int N = 10; int max_tgt_len = 500; - int n_embd = llama_n_embd(mymodel->ctx); + int n_embd = llama_n_embd(llama_get_model(mymodel->ctx)); // add random float embd to test evaluation float * data = new float[N*n_embd]; -- cgit v1.2.3