vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

llama : make model stateless and context stateful (llama_state) (#1797)

Browse source 
* llama : make model stateless and context stateful

* llama : minor cleanup

* llama : update internal API declaration

* Apply suggestions from code review

fix style

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

* Missing model memory release

* Fix style

* Add deprecated warning for public API function llama_init_from_file

* Update public API use cases: move away from deprecated llama_init_from_file

* Deprecate public API function llama_apply_lora_from_file

---------

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Didzis Gosko 2023-06-24 11:47:58 +03:00 • committed by GitHub
parent d7b7484f74
commit 527b6fba1d
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
13 changed files with 244 additions and 92 deletions
Download patch file Download diff file Expand all files Collapse all files

15
examples/quantize-stats/quantize-stats.cpp
View file

@ -320,6 +320,7 @@ int main(int argc, char ** argv) {
fprintf(stderr, "Loading model\n");
const int64_t t_main_start_us = ggml_time_us();
llama_model * model;
llama_context * ctx;
{
@ -330,10 +331,18 @@ int main(int argc, char ** argv) {
lparams.f16_kv = false;
lparams.use_mlock = false;
ctx = llama_init_from_file(params.model.c_str(), lparams);
model = llama_load_model_from_file(params.model.c_str(), lparams);
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);
if (ctx == NULL) {
fprintf(stderr, "%s: error: failed to load model '%s'\n", __func__, params.model.c_str());
fprintf(stderr, "%s: error: failed to create context with model '%s'\n", __func__, params.model.c_str());
llama_free_model(model);
return 1;
}
}
@ -357,6 +366,7 @@ int main(int argc, char ** argv) {
fprintf(stderr, "%s: error: Quantization should be tested with a float model, "
"this model contains already quantized layers (%s is type %d)\n", __func__, kv_tensor.first.c_str(), kv_tensor.second->type);
llama_free(ctx);
llama_free_model(model);
return 1;
}
included_layers++;
@ -415,6 +425,7 @@ int main(int argc, char ** argv) {
llama_free(ctx);
llama_free_model(model);
// report timing
{
const int64_t t_main_end_us = ggml_time_us();