mikhail/llama.cpp-mtp-turboquant
1
0
Fork 0
Code Issues Pull Requests Actions 28 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
examples/lookup/lookup-create.cpp
+4 -4
View File
@@ -18,16 +18,16 @@ int main(int argc, char ** argv){
llama_numa_init(params.numa);
// load the model
common_init_result llama_init = common_init_from_params(params);
auto llama_init = common_init_from_params(params);
llama_model_ptr & model = llama_init.model;
llama_context_ptr & ctx = llama_init.context;
auto * model = llama_init->model();
auto * ctx = llama_init->context();
GGML_ASSERT(model != nullptr);
// tokenize the prompt
std::vector<llama_token> inp;
inp = common_tokenize(ctx.get(), params.prompt, true, true);
inp = common_tokenize(ctx, params.prompt, true, true);
fprintf(stderr, "%s: tokenization done\n", __func__);
common_ngram_cache ngram_cache;