vrr/koboldcpp
2
0
Fork 0
mirror of https://github.com/LostRuins/koboldcpp.git synced 2025-09-10 09:04:36 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'upstream' into concedo_experimental

Browse source 
# Conflicts:
#	.devops/tools.sh
#	build-xcframework.sh
#	ci/run.sh
#	examples/Miku.sh
#	examples/chat-13B.sh
#	examples/chat-persistent.sh
#	examples/chat-vicuna.sh
#	examples/chat.sh
#	examples/jeopardy/jeopardy.sh
#	examples/reason-act.sh
#	examples/server-llama2-13B.sh
#	examples/sycl/build.sh
#	examples/sycl/run-llama2.sh
#	examples/sycl/run-llama3.sh
#	examples/ts-type-to-grammar.sh
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-sycl/element_wise.cpp
#	ggml/src/ggml-sycl/element_wise.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	scripts/apple/validate-apps.sh
#	scripts/apple/validate-ios.sh
#	scripts/apple/validate-macos.sh
#	scripts/apple/validate-tvos.sh
#	scripts/apple/validate-visionos.sh
#	scripts/check-requirements.sh
#	scripts/ci-run.sh
#	scripts/compare-commits.sh
#	scripts/debug-test.sh
#	scripts/gen-authors.sh
#	scripts/get-hellaswag.sh
#	scripts/get-pg.sh
#	scripts/get-wikitext-103.sh
#	scripts/get-wikitext-2.sh
#	scripts/get-winogrande.sh
#	scripts/hf.sh
#	scripts/qnt-all.sh
#	scripts/run-all-perf.sh
#	scripts/run-all-ppl.sh
#	scripts/sync-ggml-am.sh
#	scripts/sync-ggml.sh
#	scripts/tool_bench.sh
#	tests/test-backend-ops.cpp
#	tests/test-lora-conversion-inference.sh
#	tests/test-tokenizer-0.sh
#	tools/server/README.md
This commit is contained in:
Concedo 2025-06-30 20:38:44 +08:00
commit cdda9d16e0
42 changed files with 1519 additions and 118 deletions
Download patch file Download diff file Expand all files Collapse all files

10
common/arg.cpp
View file

@ -2796,6 +2796,16 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
params.ssl_file_cert = value;
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_ARG_SSL_CERT_FILE"));
add_opt(common_arg(
{"--chat-template-kwargs"}, "STRING",
string_format("sets additional params for the json template parser"),
[](common_params & params, const std::string & value) {
auto parsed = json::parse(value);
for (const auto & item : parsed.items()) {
params.default_template_kwargs[item.key()] = item.value().dump();
}
}
).set_examples({LLAMA_EXAMPLE_SERVER}).set_env("LLAMA_CHAT_TEMPLATE_KWARGS"));
add_opt(common_arg(
{"-to", "--timeout"}, "N",
string_format("server read/write timeout in seconds (default: %d)", params.timeout_read),