Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-19 01:05:09 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	docs/backend/SYCL.md
#	docs/backend/snapdragon/developer.md
#	examples/convert-llama2c-to-ggml/convert-llama2c-to-ggml.cpp
#	examples/sycl/run-llama2.sh
#	examples/sycl/start-svr.sh
#	examples/sycl/test.sh
#	examples/sycl/win-run-llama2.bat
#	examples/sycl/win-start-svr.bat
#	examples/sycl/win-test.bat
#	ggml/CMakeLists.txt
#	ggml/src/ggml-et/et-kernels/src/ssm_scan_f32.c
#	ggml/src/ggml-et/ggml-et-ops.cpp
#	ggml/src/ggml-et/ggml-et-ops.h
#	ggml/src/ggml-sycl/ssm_scan.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	ggml/src/ggml-webgpu/wgsl-shaders/ssm_scan.wgsl
#	scripts/bench-models.sh
#	scripts/snapdragon/adb/run-bench.sh
#	scripts/snapdragon/adb/run-cli.sh
#	scripts/snapdragon/adb/run-completion.sh
#	scripts/snapdragon/adb/run-mtmd.sh
#	scripts/snapdragon/windows/run-bench.ps1
#	scripts/snapdragon/windows/run-cli.ps1
#	scripts/snapdragon/windows/run-completion.ps1
#	scripts/snapdragon/windows/run-mtmd.ps1
#	scripts/sync-ggml.last
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-chat.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/README.md
#	tools/server/README.md
This commit is contained in:
Concedo
2026-08-15 22:50:04 +08:00
parent 531cac9cd3 adb55e5148
commit 82e15c08bf
60 changed files with 1781 additions and 447 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+15
View File
@@ -3647,6 +3647,18 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_REASONING"));
add_opt(common_arg(
{"--reasoning-effort"}, "LEVEL",
"reasoning effort level given to the chat template: 'default' to keep the template default,\n"
"or a level such as 'minimal', 'low', 'medium', 'high', 'xhigh' or 'max' (default: default)",
[](common_params & params, const std::string & value) {
if (value == "default") {
params.default_template_kwargs.erase("reasoning_effort");
} else {
params.default_template_kwargs["reasoning_effort"] = json(value).dump();
}
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_COMPLETION, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_REASONING_EFFORT"));
add_opt(common_arg(
{"--reasoning-budget"}, "N",
"token budget for thinking: -1 for unrestricted, 0 for immediate end, N>0 for token budget (default: -1)",
@@ -4066,6 +4078,9 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"--spec-draft-n-max"}, "N",
string_format("number of tokens to draft for speculative decoding (default: %d)", params.speculative.draft.n_max),
[](common_params & params, int value) {
if (value < 0) {
throw std::invalid_argument("invalid value");
}
params.speculative.draft.n_max = value;
}
).set_spec().set_examples({LLAMA_EXAMPLE_SPECULATIVE, LLAMA_EXAMPLE_LOOKUP, LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}).set_env("LLAMA_ARG_SPEC_DRAFT_N_MAX"));