Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-18 16:55:14 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/release.yml
#	SECURITY.md
#	common/CMakeLists.txt
#	docs/speculative.md
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f16.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32.cl
#	ggml/src/ggml-opencl/kernels/flash_attn_f32_f16.cl
#	ggml/src/ggml-opencl/kernels/set_rows.cl
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-sycl/norm.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat-template.cpp
#	tests/test-chat.cpp
#	tests/test-export-graph-ops.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tools/rpc/CMakeLists.txt
#	tools/rpc/README.md
This commit is contained in:
Concedo
2026-06-29 16:43:44 +08:00
parent 0677ddd19d 277a105dc8
commit 3b867bd4b1
40 changed files with 1523 additions and 558 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+16 -2
View File
@@ -468,7 +468,7 @@ void common_models_handler_apply(common_models_handler & handler, common_params
// the first part is what gets loaded, so point params.model.path at it
if (!url_tasks.empty()) {
std::string first_path = url_tasks.front().local_path;
url_tasks.front().on_done = [&]() { params.model.path = first_path; };
url_tasks.front().on_done = [&, first_path]() { params.model.path = first_path; };
}
for (auto & task : url_tasks) {
tasks.push_back(std::move(task));
@@ -3297,6 +3297,20 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.sampling.reasoning_budget_message = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_THINK_BUDGET_MESSAGE"));
add_opt(common_arg(
{"--reasoning-preserve"},
{"--no-reasoning-preserve"},
"preserve reasoning trace in the full history, not just the last assistant message (default: template default)\n"
"compatible with certain templates having 'supports_preserve_reasoning' capability\n"
"example: https://docs.z.ai/guides/capabilities/thinking-mode#preserved-thinking",
[](common_params & params, bool value) {
if (value) {
params.default_template_kwargs["preserve_reasoning"] = "true";
} else {
params.default_template_kwargs["preserve_reasoning"] = "false";
}
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_REASONING_PRESERVE"));
add_opt(common_arg(
{"--chat-template"}, "JINJA_TEMPLATE",
string_format(
@@ -3472,7 +3486,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.offline = true;
}
).set_env("LLAMA_ARG_OFFLINE"));
).set_examples({LLAMA_EXAMPLE_COMMON, LLAMA_EXAMPLE_DOWNLOAD}).set_env("LLAMA_ARG_OFFLINE"));
add_opt(common_arg(
{"-lv", "--verbosity", "--log-verbosity"}, "N",
string_format("Set the verbosity threshold. Messages with a higher verbosity will be ignored. Values:\n"