Public/koboldcpp
1
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2026-09-09 22:39:13 +02:00
Code Issues Packages Projects Releases Wiki Activity

Merge branch 'upstream' into concedo_experimental

Browse Source 
# Conflicts:
#	.devops/nix/package.nix
#	.github/workflows/server.yml
#	docs/development/HOWTO-add-model.md
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp/CMakeLists.txt
#	ggml/src/ggml-hexagon/htp/argsort-ops.c
#	ggml/src/ggml-hexagon/htp/concat-ops.c
#	ggml/src/ggml-hexagon/htp/flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/gated-delta-net-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-flash-attn-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-matmul-ops.c
#	ggml/src/ggml-hexagon/htp/hmx-ops.h
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/hvx-utils.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/pad-ops.c
#	ggml/src/ggml-hexagon/htp/unary-ops.c
#	ggml/src/ggml-opencl/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/cvt.cl
#	ggml/src/ggml-webgpu/wgsl-shaders/cpy.wgsl
#	scripts/sync_vendor.py
#	src/llama-context.cpp
#	tests/test-backend-sampler.cpp
#	tools/server/README.md
#	tools/ui/tests/stories/ChatScreenForm.a11y.stories.svelte
This commit is contained in:
Concedo
2026-06-02 19:28:39 +08:00
parent 153214c66a d5ab0834ab
commit 13eaa04269
78 changed files with 1801 additions and 477 deletions
Download Patch File Download Diff File Expand all files Collapse all files
common/arg.cpp
-6
View File
@@ -1042,11 +1042,9 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
// we define here to make sure it's included in llama-gen-docs
if (ex == LLAMA_EXAMPLE_COMPLETION) {
params.use_jinja = false; // disable jinja by default
} else if (ex == LLAMA_EXAMPLE_MTMD) {
params.use_jinja = false; // disable jinja by default
params.sampling.temp = 0.2; // lower temp by default for better quality
} else if (ex == LLAMA_EXAMPLE_SERVER) {
params.n_parallel = -1; // auto by default
}
@@ -1067,7 +1065,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
sampler_type_names.pop_back(); // remove last semicolon
}
/**
* filter options by example
* rules:
@@ -1081,7 +1078,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
}
};
add_opt(common_arg(
{"-h", "--help", "--usage"},
"print usage and exit",
@@ -4082,7 +4078,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.sampling.top_k = 0;
params.sampling.min_p = 0.01f;
params.use_jinja = true;
//params.default_template_kwargs["reasoning_effort"] = "\"high\"";
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));
@@ -4101,7 +4096,6 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.sampling.top_k = 0;
params.sampling.min_p = 0.01f;
params.use_jinja = true;
//params.default_template_kwargs["reasoning_effort"] = "\"high\"";
}
).set_examples({LLAMA_EXAMPLE_SERVER, LLAMA_EXAMPLE_CLI}));