upstream-archive/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2026-07-23 11:10:55 -05:00
Code Issues Packages Projects Releases Wiki Activity

Add support for Laguna XS.2 & M.1 (#25165)

Browse Source
This commit is contained in:
Joe Rowell
2026-07-22 03:54:08 +02:00
committed by GitHub
parent 66e4bf7e59
commit 1f66c3ce1c
22 changed files with 1091 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

20
common/chat-diff-analyzer.cpp
View File

@@ -173,6 +173,26 @@ static std::vector<std::function<void(const common_chat_template & tmpl, autopar
LOG_DBG(ANSI_ORANGE "[Patch: JSON name/parameters tool instruction]\n" ANSI_RESET);
}
},
// Laguna (poolside) - the v4 chat template renders reasoning and tool-arg
// delimiters with formatting whitespace ("<think>\n", "</arg_value>\n") that
// the model does not emit, so the inferred delimiters carry a spurious
// newline and never match the model output. Trim to the bare tag. (v8
// renders without the whitespace, so this is a no-op there.)
[](const common_chat_template & tmpl, autoparser & analysis) -> void {
if (tmpl.src.find("laguna_glm_thinking") != std::string::npos) {
analysis.reasoning.start = trim_whitespace(analysis.reasoning.start);
analysis.reasoning.end = trim_whitespace(analysis.reasoning.end);
analysis.tools.arguments.value_prefix = trim_whitespace(analysis.tools.arguments.value_prefix);
analysis.tools.arguments.value_suffix = trim_whitespace(analysis.tools.arguments.value_suffix);
analysis.tools.arguments.separator = trim_whitespace(analysis.tools.arguments.separator);
analysis.tools.arguments.tolerate_intertag_whitespace = true;
// The CONTROL/eot </assistant> token only halts generation when emitted as the
// single token; after tool calls the model can spell it out as text tokens.
// A literal stop string catches it either way.
analysis.additional_stops.push_back("</assistant>");
LOG_DBG(ANSI_ORANGE "[Patch: Laguna]\n" ANSI_RESET);
}
},
});