ikawrakow/ik_llama.cpp
1
0
Fork 0
mirror of https://github.com/ikawrakow/ik_llama.cpp.git synced 2026-02-20 05:04:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

spec : add self speculative decoding, ngram and refactor (#1261)

Browse Source 
* spec : add self speculative decoding and ngram-mod and refactor

common : use common_ prefix for common library function

llama : use LLAMA_TOKEN_NULL

spec : add self speculative decoding (no draft model required) + refactor

spec : add ngram-mod

spec : various improvements ton ngram-map + docs

spec : fix the check-rate logic of ngram-simple

common : add common_speculative_is_compat()

spec : simplify time measurement using common_time_meas

refactor common_sampler_init

refactor common_token_to_piece

refactor and fix cur_p bug

clean up

* spec : remove check rate

* spec: show warnings instead of abort

---------

Co-authored-by: firecoperana <firecoperana>
Co-authored-by: Sascha Rogmann <59577610+srogmann@users.noreply.github.com>
This commit is contained in:
firecoperana
2026-02-13 12:04:55 -06:00
committed by GitHub
parent 1fdbc0dafe
commit 1cb7e1bf39
54 changed files with 2652 additions and 779 deletions
Download Patch File Download Diff File Expand all files Collapse all files

10
examples/simple/simple.cpp
View File

@@ -35,9 +35,9 @@ int main(int argc, char ** argv) {
// initialize the model
llama_model_params model_params = llama_model_params_from_gpt_params(params);
llama_model_params model_params = common_model_params_to_llama(params);
llama_model * model = llama_load_model_from_file(params.model.c_str(), model_params);
llama_model * model = llama_model_load_from_file(params.model.c_str(), model_params);
if (model == NULL) {
fprintf(stderr , "%s: error: unable to load model\n" , __func__);
@@ -46,9 +46,9 @@ int main(int argc, char ** argv) {
// initialize the context
llama_context_params ctx_params = llama_context_params_from_gpt_params(params);
llama_context_params ctx_params = common_context_params_to_llama(params);
llama_context * ctx = llama_new_context_with_model(model, ctx_params);
llama_context * ctx = llama_init_from_model(model, ctx_params);
if (ctx == NULL) {
fprintf(stderr , "%s: error: failed to create the llama_context\n" , __func__);
@@ -58,7 +58,7 @@ int main(int argc, char ** argv) {
// tokenize the prompt
std::vector<llama_token> tokens_list;
tokens_list = ::llama_tokenize(ctx, params.prompt, true);
tokens_list = ::common_tokenize(ctx, params.prompt, true);
const int n_ctx = llama_n_ctx(ctx);
const int n_kv_req = tokens_list.size() + (n_predict - tokens_list.size());