Server: refactor and rename functions (#1151)

* Server: rename functions and refactor code

rename functions

refactor update slots

rename params_base

rename timings

* change

* Revert kv cache name changes

* Revert 2

* fix test build error

---------

Co-authored-by: firecoperana <firecoperana>
This commit is contained in:
firecoperana
2026-01-18 00:16:57 -06:00
committed by GitHub
parent 7024fdbc72
commit d71a3ec315
38 changed files with 532 additions and 528 deletions

View File

@@ -78,7 +78,7 @@ int main(int argc, char **argv) {
const int n_vocab = llama_n_vocab(model);
for (int i = 0; i < n_vocab; ++i) {
std::string str = llama_detokenize(ctx, std::vector<int>(1, i));
std::string str = common_token_to_piece(ctx, std::vector<int>(1, i));
try {
auto cps = unicode_cpts_from_utf8(str);
std::vector<llama_token> tokens = llama_tokenize(ctx, str, false, true);
@@ -94,7 +94,7 @@ int main(int argc, char **argv) {
fprintf(stderr, "]\n");
return 2;
}
std::string check = llama_detokenize(ctx, tokens);
std::string check = common_token_to_piece(ctx, tokens);
if (check != str) {
fprintf(stderr, "%s : error: token %d detokenizes to '%s'(%zu) but tokenization of this detokenizes to '%s'(%zu)\n",
__func__, i, str.c_str(), str.length(), check.c_str(), check.length());
@@ -124,7 +124,7 @@ int main(int argc, char **argv) {
std::string str = unicode_cpt_to_utf8(cp);
std::vector<llama_token> tokens = llama_tokenize(ctx, str, false);
std::string check = llama_detokenize(ctx, tokens);
std::string check = common_token_to_piece(ctx, tokens);
if (cp != 9601 && str != check) {
fprintf(stderr, "error: codepoint 0x%x detokenizes to '%s'(%zu) instead of '%s'(%zu)\n",
cp, check.c_str(), check.length(), str.c_str(), str.length());