vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-11 01:24:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.github/actions/windows-setup-curl/action.yml
#	.github/workflows/build-linux-cross.yml
#	README.md
#	common/CMakeLists.txt
#	examples/parallel/README.md
#	examples/parallel/parallel.cpp
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-vulkan/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo 2025-05-18 23:27:53 +08:00
commit 59300dbdf5
25 changed files with 694 additions and 550 deletions
Download patch file Download diff file Expand all files Collapse all files

14
common/arg.cpp
View file

@ -2586,7 +2586,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params, int value) {
params.n_junk = value;
}
).set_examples({LLAMA_EXAMPLE_PASSKEY}));
).set_examples({LLAMA_EXAMPLE_PASSKEY, LLAMA_EXAMPLE_PARALLEL}));
add_opt(common_arg(
{"--pos"}, "N",
string_format("position of the passkey in the junk text (default: %d)", params.i_pos),
@ -2649,7 +2649,7 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
[](common_params & params) {
params.is_pp_shared = true;
}
).set_examples({LLAMA_EXAMPLE_BENCH}));
).set_examples({LLAMA_EXAMPLE_BENCH, LLAMA_EXAMPLE_PARALLEL}));
add_opt(common_arg(
{"-npp"}, "n0,n1,...",
"number of prompt tokens",
@ -2881,6 +2881,16 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.chat_template = read_file(value);
}
).set_examples({LLAMA_EXAMPLE_MAIN, LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_CHAT_TEMPLATE_FILE"));
add_opt(common_arg(
{"--no-prefill-assistant"},
string_format(
"whether to prefill the assistant's response if the last message is an assistant message (default: prefill enabled)\n"
"when this flag is set, if the last message is an assistant message then it will be treated as a full message and not prefilled\n"
),
[](common_params & params) {
params.prefill_assistant = false;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_NO_PREFILL_ASSISTANT"));
add_opt(common_arg(
{"-sps", "--slot-prompt-similarity"}, "SIMILARITY",
string_format("how much the prompt of a request must match the prompt of a slot in order to use that slot (default: %.2f, 0.0 = disabled)\n", params.slot_prompt_similarity),