Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 09:15:18 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	docs/ops.md
#	docs/ops/WebGPU.csv
#	embd_res/templates/stepfun-ai-Step-3.5-Flash.jinja
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/unary.wgsl
#	src/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tools/mtmd/CMakeLists.txt
This commit is contained in:
Concedo
2026-02-20 15:16:26 +08:00
parent 07c45ced56 77d6ae4ac8
commit e626de2430
26 changed files with 618 additions and 29 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/chat.cpp
+6 -5
View File
@@ -2057,6 +2057,7 @@ static common_chat_params common_chat_params_init_gpt_oss(const common_chat_temp
if (has_reasoning_content && has_tool_calls) {
auto adjusted_message = msg;
adjusted_message["thinking"] = msg.at("reasoning_content");
adjusted_message.erase("content");
adjusted_messages.push_back(adjusted_message);
} else {
adjusted_messages.push_back(msg);
@@ -3154,15 +3155,15 @@ static common_chat_params common_chat_templates_apply_jinja(
}
// Qwen3-Coder XML format detection (must come before Hermes 2 Pro)
// Detect via explicit XML markers unique to Qwen3-Coder to avoid false positives in other templates.
// Require presence of <tool_call>, <function=...>, and <parameter=...> blocks.
// Detect via XML markers: <tool_call>, <function=...>, and <parameter=...> blocks.
// Also matches Step-3.5-Flash and Nemotron 3 Nano which use the same output format.
if (src.find("<tool_call>") != std::string::npos &&
src.find("<function>") != std::string::npos &&
src.find("<function=") != std::string::npos &&
src.find("<parameters>") != std::string::npos &&
src.find("<parameter=") != std::string::npos) {
workaround::func_args_not_string(params.messages);
// Nemotron 3 Nano 30B A3B
// Models with <think> support (Step-3.5-Flash, Nemotron 3 Nano) use the
// Nemotron v3 PEG parser for streaming and schema-aware parameter parsing.
// Qwen3-Coder has no <think> in its template.
if (src.find("<think>") != std::string::npos) {
return common_chat_params_init_nemotron_v3(tmpl, params);
}