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 commit '3ca19b0e9f3f4f444d22c9f509805d037a611847' into concedo_experimental

Browse Source 
# Conflicts:
#	.github/workflows/build.yml
#	common/CMakeLists.txt
#	common/chat-peg-parser.cpp
#	docs/backend/SYCL.md
#	docs/ops.md
#	docs/ops/SYCL.csv
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/convert.hpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/norm.cpp
#	ggml/src/ggml-sycl/rope.cpp
#	ggml/src/ggml-sycl/rope.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_decls.tmpl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_reg_tile.wgsl
#	ggml/src/ggml-webgpu/wgsl-shaders/mul_mat_vec.wgsl
#	scripts/compare-llama-bench.py
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tools/cli/cli.cpp
This commit is contained in:
Concedo
2026-03-15 11:11:31 +08:00
parent 3b9385a627 3ca19b0e9f
commit 67c9798d0b
41 changed files with 836 additions and 212 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+31 -2
View File
@@ -2916,6 +2916,10 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params, const std::string & value) {
auto parsed = json::parse(value);
for (const auto & item : parsed.items()) {
if (item.key() == "enable_thinking") {
LOG_WRN("Setting 'enable_thinking' via --chat-template-kwargs is deprecated. "
"Use --reasoning on / --reasoning off instead.\n");
}
params.default_template_kwargs[item.key()] = item.value().dump();
}
}
@@ -3051,14 +3055,39 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.reasoning_format = common_reasoning_format_from_name(value);
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_THINK"));
add_opt(common_arg(
{"-rea", "--reasoning"}, "[on|off|auto]",
"Use reasoning/thinking in the chat ('on', 'off', or 'auto', default: 'auto' (detect from template))",
[](common_params & params, const std::string & value) {
if (is_truthy(value)) {
params.enable_reasoning = 1;
params.default_template_kwargs["enable_thinking"] = "true";
} else if (is_falsey(value)) {
params.enable_reasoning = 0;
params.default_template_kwargs["enable_thinking"] = "false";
} else if (is_autoy(value)) {
params.enable_reasoning = -1;
} else {
throw std::invalid_argument(
string_format("error: unknown value for --reasoning: '%s'\n", value.c_str()));
}
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_REASONING"));
add_opt(common_arg(
{"--reasoning-budget"}, "N",
"controls the amount of thinking allowed; currently only one of: -1 for unrestricted thinking budget, or 0 to disable thinking (default: -1)",
"token budget for thinking: -1 for unrestricted, 0 for immediate end, N>0 for token budget (default: -1)",
[](common_params & params, int value) {
if (value != 0 && value != -1) { throw std::invalid_argument("invalid value"); }
if (value < -1) { throw std::invalid_argument("invalid value"); }
params.reasoning_budget = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_THINK_BUDGET"));
add_opt(common_arg(
{"--reasoning-budget-message"}, "MESSAGE",
"message injected before the end-of-thinking tag when reasoning budget is exhausted (default: none)",
[](common_params & params, const std::string & value) {
params.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(
{"--chat-template"}, "JINJA_TEMPLATE",
string_format(