From b804b1ef77351d2a11be945462c6c251710476cb Mon Sep 17 00:00:00 2001 From: Pierrick Hymbert Date: Thu, 11 Apr 2024 14:51:07 +0200 Subject: eval-callback: Example how to use eval callback for debugging (#6576) * gguf-debug: Example how to use ggml callback for debugging * gguf-debug: no mutex, verify type, fix stride. * llama: cv eval: move cb eval field in common gpt_params * ggml_debug: use common gpt_params to pass cb eval. Fix get tensor SIGV random. * ggml_debug: ci: add tests * ggml_debug: EOL in CMakeLists.txt * ggml_debug: Remove unused param n_batch, no batching here * ggml_debug: fix trailing spaces * ggml_debug: fix trailing spaces * common: fix cb_eval and user data not initialized * ci: build revert label * ggml_debug: add main test label * doc: add a model: add a link to ggml-debug * ggml-debug: add to make toolchain * ggml-debug: tests add the main label * ggml-debug: ci add test curl label * common: allow the warmup to be disabled in llama_init_from_gpt_params * ci: add curl test * ggml-debug: better tensor type support * gitignore : ggml-debug * ggml-debug: printing also the sum of each tensor * ggml-debug: remove block size * eval-callback: renamed from ggml-debug * eval-callback: fix make toolchain --------- Co-authored-by: slaren Co-authored-by: Georgi Gerganov --- examples/imatrix/imatrix.cpp | 26 ++++++++++---------------- 1 file changed, 10 insertions(+), 16 deletions(-) (limited to 'examples/imatrix/imatrix.cpp') diff --git a/examples/imatrix/imatrix.cpp b/examples/imatrix/imatrix.cpp index 1bf55f90..ff624c53 100644 --- a/examples/imatrix/imatrix.cpp +++ b/examples/imatrix/imatrix.cpp @@ -597,24 +597,18 @@ int main(int argc, char ** argv) { llama_backend_init(); llama_numa_init(params.numa); - llama_model_params mparams = llama_model_params_from_gpt_params(params); - - llama_model * model = llama_load_model_from_file(params.model.c_str(), mparams); - if (model == NULL) { - fprintf(stderr, "%s: error: unable to load model\n", __func__); - return 1; - } - - llama_context_params cparams = llama_context_params_from_gpt_params(params); - // pass the callback to the backend scheduler // it will be executed for each node during the graph computation - cparams.cb_eval = ik_collect_imatrix; - cparams.cb_eval_user_data = NULL; - - llama_context * ctx = llama_new_context_with_model(model, cparams); - if (ctx == NULL) { - fprintf(stderr, "%s: error: unable to create context\n", __func__); + params.cb_eval = ik_collect_imatrix; + params.cb_eval_user_data = NULL; + params.warmup = false; + + // init + llama_model * model; + llama_context * ctx; + std::tie(model, ctx) = llama_init_from_gpt_params(params); + if (model == nullptr || ctx == nullptr) { + fprintf(stderr, "%s : failed to init\n", __func__); return 1; } -- cgit v1.2.3