tests : consolidate context state tests into test-llama-context (#30023)
* 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
This commit is contained in:
1 parent
b476d9a762
commit
a17e94d229
27 files changed
+2772
-1965
No files matched your search
@@ -312,10 +312,14 @@ llama_kv_cache::llama_kv_cache(
|
||||
n_rot_k = other->n_rot_k;
|
||||
n_rot_v = other->n_rot_v;
|
||||
} else {
|
||||
const char * LLAMA_ATTN_ROT_DISABLE = getenv("LLAMA_ATTN_ROT_DISABLE");
|
||||
const bool attn_rot_disable = LLAMA_ATTN_ROT_DISABLE ? atoi(LLAMA_ATTN_ROT_DISABLE) : false;
|
||||
// two knobs turn the same thing off: the environment variable, for the whole process, and
|
||||
// the model setting, for the contexts of one model - see llama_model_set_attn_rot
|
||||
const char * env_rot_disable = getenv("LLAMA_ATTN_ROT_DISABLE");
|
||||
|
||||
const bool attn_rot_disable = !model.attn_rot || (env_rot_disable != nullptr && atoi(env_rot_disable) != 0);
|
||||
if (attn_rot_disable) {
|
||||
LLAMA_LOG_WARN("%s: attention rotation force disabled (LLAMA_ATTN_ROT_DISABLE)\n", __func__);
|
||||
LLAMA_LOG_WARN("%s: attention rotation force disabled (%s)\n", __func__,
|
||||
model.attn_rot ? "LLAMA_ATTN_ROT_DISABLE" : "llama_model_set_attn_rot");
|
||||
}
|
||||
|
||||
bool attn_rot_k =
|
||||
|
||||
Reference in new issue
Block a user