tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-27 12:05:03 +00:00
Code Issues Packages Projects Releases Wiki Activity

server : smart slot selection using Longest Common Prefix (#7728)

Browse Source 
* server : Smart selection of available slot using Longest Common Substring

* add usage

* remove trailing whitespaces

* Use Longest Common Prefix (LCP) instead of LCS

* Rename argument
This commit is contained in:
sasha0552
2024-06-08 07:50:31 +00:00
committed by GitHub
parent da799b4189
commit 7a16ce7db2
4 changed files with 140 additions and 17 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
examples/server/utils.hpp
View File

@ -253,6 +253,13 @@ static size_t common_part(const std::vector<llama_token> & a, const std::vector<
return i;
}
static size_t common_part(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++) {}
return i;
}
static bool ends_with(const std::string & str, const std::string & suffix) {
return str.size() >= suffix.size() && 0 == str.compare(str.size() - suffix.size(), suffix.size(), suffix);
}