Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-20 01:31:42 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/openvino.Dockerfile
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/build.yml
#	common/chat.cpp
#	docs/backend/OPENVINO.md
#	examples/speculative-simple/speculative-simple.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/libggml-htp.inf
#	ggml/src/ggml-openvino/ggml-decoder.cpp
#	ggml/src/ggml-openvino/ggml-openvino-extra.cpp
#	ggml/src/ggml-openvino/ggml-openvino.cpp
#	ggml/src/ggml-openvino/ggml-quants.cpp
#	ggml/src/ggml-openvino/openvino/op/rope.cpp
#	ggml/src/ggml-openvino/openvino/op_table.cpp
#	ggml/src/ggml-openvino/openvino/op_table.h
#	ggml/src/ggml-openvino/openvino/translate_session.cpp
#	ggml/src/ggml-openvino/openvino/utils.cpp
#	ggml/src/ggml-openvino/openvino/utils.h
#	ggml/src/ggml-openvino/utils.cpp
#	ggml/src/ggml-openvino/utils.h
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/convert.cpp
#	ggml/src/ggml-sycl/convert.hpp
#	ggml/src/ggml-sycl/gemm.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/set_rows.cpp
#	ggml/src/ggml-webgpu/ggml-webgpu-shader-lib.hpp
#	ggml/src/ggml-webgpu/ggml-webgpu.cpp
#	scripts/sync_vendor.py
#	tests/CMakeLists.txt
#	tests/test-chat.cpp
#	tools/cli/cli.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/server/CMakeLists.txt
This commit is contained in:
Concedo
2026-04-23 00:55:05 +08:00
parent becf70d49b 8bccdbbff9
commit 0755f27372
42 changed files with 1531 additions and 3199 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
+13 -2
View File
@@ -3124,14 +3124,14 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
"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 < -1) { throw std::invalid_argument("invalid value"); }
params.reasoning_budget = value;
params.sampling.reasoning_budget_tokens = 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;
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(
@@ -3904,6 +3904,17 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
add_opt(common_arg(
{"--spec-default"},
string_format("enable default speculative decoding config"),
[](common_params & params) {
params.speculative.type = COMMON_SPECULATIVE_TYPE_NGRAM_MOD;
params.speculative.ngram_size_n = 24;
params.speculative.n_min = 48;
params.speculative.n_max = 64;
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
return ctx_arg;
}