vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

server : reuse cached context chunks (#9866)

Browse source 
ggml-ci
This commit is contained in:
Georgi Gerganov 2024-10-13 18:52:48 +03:00 • committed by GitHub
parent 92be9f1216
commit c7181bd294
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
5 changed files with 78 additions and 6 deletions
Download patch file Download diff file Expand all files Collapse all files

4
examples/server/utils.hpp
View file

@ -195,14 +195,14 @@ static std::string gen_chatcmplid() {
// other common utils
//
static size_t common_part(const std::vector<llama_token> & a, const std::vector<llama_token> & b) {
static size_t longest_common_prefix(const std::vector<llama_token> & a, const std::vector<llama_token> & b) {
size_t i;
for (i = 0; i < a.size() && i < b.size() && a[i] == b[i]; i++) {}
return i;
}
static size_t common_part(const std::string & a, const std::string & b) {
static size_t longest_common_prefix(const std::string & a, const std::string & b) {
size_t i;
for (i = 0; i < a.size() && i < b.size() && a[i] == b[i]; i++) {}