sdgoij/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-03-17 16:44:07 +00:00
Code Issues Packages Projects Releases Wiki Activity

common : refactor common_sampler + grammar logic changes (#17937)

Browse Source 
* common : refactor common_sampler + grammar logic changes

* tests : increase max_tokens to get needed response

* batched : fix uninitialized samplers
This commit is contained in:
Georgi Gerganov
2025-12-14 10:11:13 +02:00
committed by GitHub
parent 3238b1400c
commit 254098a279
27 changed files with 372 additions and 293 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tools/perplexity/perplexity.cpp
View File

@@ -2024,10 +2024,10 @@ int main(int argc, char ** argv) {
llama_numa_init(params.numa);
// load the model and apply lora adapter, if any
common_init_result llama_init = common_init_from_params(params);
auto llama_init = common_init_from_params(params);
llama_model * model = llama_init.model.get();
llama_context * ctx = llama_init.context.get();
auto * model = llama_init->model();
auto * ctx = llama_init->context();
if (model == NULL) {
LOG_ERR("%s: unable to load model\n", __func__);