Georgi Gerganov
a17e94d229
* tests : consolidate the context state tests into test-llama-context test-save-load-state, test-recurrent-state-rollback and test-state-restore-fragmented check the same object from three places: the KV cache and the recurrent state of a llama_context, saved, loaded, copied, rolled back. Each had its own main, its own loop over the models, its own copy of the token and the comparison helpers, and a run of all three loaded the same models several times. They are one binary now, and the case is the unit of the test: tests/llama-context/test-case.h the interface a case implements tests/llama-context/cases-kv.cpp the cases of the KV cache tests/llama-context/cases-rs.cpp the cases of the recurrent state tests/llama-context/test-util.cpp tokens, generation, comparison tests/llama-context/test-runner.cpp the models of a case, on threads tests/llama-context/test-log.cpp the log file of a model A run is a table: a row per model, a column per case, a cell holds the verdict of that pair. The models load on several threads (-j, --threads, min(cores, 4) by default), the table is printed when it is complete and the log of a model that failed is printed after it, in the order of the rows. A case returns a verdict and the reason for it, and the runner is the only one who reports - the test does not use tests/testing.h, a run over 130 models is a matrix of verdicts and not a tree of subtests. Staging no longer travels through the environment: llama_model_set_attn_rot replaces the LLAMA_ATTN_ROT_DISABLE variable, which a model loaded in one thread used to change for the models the other threads were loading, and llama_memory_get_buffers is added for the cases that copy the buffers of a memory. common_log_set_stdo keeps the console quiet while the table is being built. ggml_aligned_malloc allocates with posix_memalign when the thread sanitizer is on. On macOS it allocates with the Mach VM, which the sanitizer does not intercept, so it never sees a page range change hands and reports the first write into recycled memory as a race - 30 of them in this test, and every one of them false. Assisted-by: pi:llama.cpp/Qwen3.8-Flash-Next * cont : run single-threaded by default * cont : try to build the tests on all platforms * cont : trim down some body fat * cont : fix * cont : fix the fix
24 lines
684 B
C++
24 lines
684 B
C++
#pragma once
|
|
|
|
#include "test-case.h"
|
|
|
|
#include <string>
|
|
#include <vector>
|
|
|
|
//
|
|
// the runner: the single place that decides how a case is executed
|
|
//
|
|
|
|
struct case_run {
|
|
std::string name;
|
|
test_status status = test_status::SKIP;
|
|
std::string reason;
|
|
};
|
|
|
|
// the cases selected by the filter, all of them when it is empty, in table order
|
|
std::vector<const ctx_test *> select_cases(const std::string & filter);
|
|
|
|
// run the selected cases for one model and return one verdict per case - with report, print the
|
|
// verdict of every case as it finishes, for single model mode
|
|
std::vector<case_run> run_cases(model_run & mr, const std::vector<const ctx_test *> & cases, bool report);
|