nikola/llama_cpp
1
0
Fork 0
Code Issues Pull Requests Actions 22 Packages Projects Releases Wiki Activity

spec : refactor params (#22397)

Browse Source 
* spec : refactor params

* cont : fix

* cont : rename "sparam" to "sampling"

* cont : add spec params category

* cont : add info about removed arguments

* cont : skip param length check for spec params

* cont : adapt server tests
This commit is contained in:
Georgi Gerganov
2026-04-28 09:07:33 +03:00
committed by GitHub
parent 516e8d7a8a
commit 14e733e36f
18 changed files with 661 additions and 409 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/lookup/lookup-create.cpp
+2 -2
View File
@@ -37,9 +37,9 @@ int main(int argc, char ** argv){
common_ngram_cache ngram_cache;
common_ngram_cache_update(ngram_cache, LLAMA_NGRAM_STATIC, LLAMA_NGRAM_STATIC, inp, inp.size(), true);
fprintf(stderr, "%s: hashing done, writing file to %s\n", __func__, params.speculative.lookup_cache_static.c_str());
fprintf(stderr, "%s: hashing done, writing file to %s\n", __func__, params.speculative.ngram_cache.lookup_cache_static.c_str());
common_ngram_cache_save(ngram_cache, params.speculative.lookup_cache_static);
common_ngram_cache_save(ngram_cache, params.speculative.ngram_cache.lookup_cache_static);
return 0;
}
examples/lookup/lookup-stats.cpp
+6 -6
View File
@@ -24,7 +24,7 @@ int main(int argc, char ** argv){
return 1;
}
const int n_draft = params.speculative.n_max;
const int n_draft = params.speculative.draft.n_max;
// init llama.cpp
llama_backend_init();
@@ -49,18 +49,18 @@ int main(int argc, char ** argv){
{
const int64_t t_start_draft_us = ggml_time_us();
if (!params.speculative.lookup_cache_static.empty()) {
if (!params.speculative.ngram_cache.lookup_cache_static.empty()) {
try {
ngram_cache_static = common_ngram_cache_load(params.speculative.lookup_cache_static);
ngram_cache_static = common_ngram_cache_load(params.speculative.ngram_cache.lookup_cache_static);
} catch (std::ifstream::failure const &) {
LOG_ERR("failed to open static lookup cache: %s", params.speculative.lookup_cache_static.c_str());
LOG_ERR("failed to open static lookup cache: %s", params.speculative.ngram_cache.lookup_cache_static.c_str());
exit(1);
}
}
if (!params.speculative.lookup_cache_dynamic.empty()) {
if (!params.speculative.ngram_cache.lookup_cache_dynamic.empty()) {
try {
ngram_cache_dynamic = common_ngram_cache_load(params.speculative.lookup_cache_dynamic);
ngram_cache_dynamic = common_ngram_cache_load(params.speculative.ngram_cache.lookup_cache_dynamic);
} catch (std::ifstream::failure const &) {} // if the file does not exist it will simply be created at the end of the program
}
examples/lookup/lookup.cpp
+7 -7
View File
@@ -25,7 +25,7 @@ int main(int argc, char ** argv){
}
// max. number of additional tokens to draft if match is found
const int n_draft = params.speculative.n_max;
const int n_draft = params.speculative.draft.n_max;
// init llama.cpp
llama_backend_init();
@@ -54,18 +54,18 @@ int main(int argc, char ** argv){
const int64_t t_start_draft_us = ggml_time_us();
common_ngram_cache_update(ngram_cache_context, LLAMA_NGRAM_MIN, LLAMA_NGRAM_MAX, inp, inp.size(), false);
if (!params.speculative.lookup_cache_static.empty()) {
if (!params.speculative.ngram_cache.lookup_cache_static.empty()) {
try {
ngram_cache_static = common_ngram_cache_load(params.speculative.lookup_cache_static);
ngram_cache_static = common_ngram_cache_load(params.speculative.ngram_cache.lookup_cache_static);
} catch (std::ifstream::failure const &) {
LOG_ERR("failed to open static lookup cache: %s", params.speculative.lookup_cache_static.c_str());
LOG_ERR("failed to open static lookup cache: %s", params.speculative.ngram_cache.lookup_cache_static.c_str());
exit(1);
}
}
if (!params.speculative.lookup_cache_dynamic.empty()) {
if (!params.speculative.ngram_cache.lookup_cache_dynamic.empty()) {
try {
ngram_cache_dynamic = common_ngram_cache_load(params.speculative.lookup_cache_dynamic);
ngram_cache_dynamic = common_ngram_cache_load(params.speculative.ngram_cache.lookup_cache_dynamic);
} catch (std::ifstream::failure const &) {} // if the file does not exist it will simply be created at the end of the program
}
@@ -213,7 +213,7 @@ int main(int argc, char ** argv){
// Update dynamic ngram cache with context ngram cache and save it to disk:
common_ngram_cache_merge(ngram_cache_dynamic, ngram_cache_context);
common_ngram_cache_save(ngram_cache_dynamic, params.speculative.lookup_cache_dynamic);
common_ngram_cache_save(ngram_cache_dynamic, params.speculative.ngram_cache.lookup_cache_dynamic);
LOG("\n\n");