ver4a/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

server: fix streaming crashes (#13786)

Browse source 
* add preludes to content on partial regex match

* allow all parsers to parse non-tool-call content.

* tweak order of <|python_tag|> vs <function= parsing for functionary v3.1 format. still not ideal but hopefully less prone to crash
This commit is contained in:
Olivier Chafik 2025-05-26 08:03:57 -07:00 • committed by GitHub
parent 88c125f2ac
commit 03f582ae8f
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 112 additions and 59 deletions
Download patch file Download diff file Expand all files Collapse all files

3
common/chat-parser.h
View file

@ -30,6 +30,7 @@ class common_chat_msg_parser {
const std::string & healing_marker() const { return healing_marker_; }
const bool & is_partial() const { return is_partial_; }
const common_chat_msg & result() const { return result_; }
const common_chat_syntax & syntax() const { return syntax_; }
void move_to(size_t pos) {
if (pos > input_.size()) {
@ -77,7 +78,7 @@ class common_chat_msg_parser {
std::vector<common_string_range> groups;
};
std::optional<find_regex_result> try_find_regex(const common_regex & regex, size_t from = std::string::npos);
std::optional<find_regex_result> try_find_regex(const common_regex & regex, size_t from = std::string::npos, bool add_prelude_to_content = true);
bool try_consume_literal(const std::string & literal);