Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/build.yml
#	ci/run.sh
#	examples/model-conversion/Makefile
#	examples/model-conversion/README.md
#	examples/model-conversion/logits.cpp
#	examples/model-conversion/requirements.txt
#	examples/model-conversion/scripts/embedding/convert-model.sh
#	examples/model-conversion/scripts/embedding/run-converted-model.sh
#	examples/model-conversion/scripts/embedding/run-original-model.py
#	examples/model-conversion/scripts/utils/semantic_check.py
#	ggml/src/ggml-cann/common.h
#	ggml/src/ggml-cann/ggml-cann.cpp
#	ggml/src/ggml-cpu/kleidiai/kernels.cpp
#	ggml/src/ggml-cpu/kleidiai/kernels.h
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-sycl/common.hpp
#	ggml/src/ggml-sycl/dpct/helper.hpp
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	ggml/src/ggml-sycl/softmax.cpp
#	ggml/src/ggml-sycl/softmax.hpp
#	requirements/requirements-all.txt
#	tests/test-chat-parser.cpp
#	tools/server/README.md
This commit is contained in:
Concedo
2025-10-09 23:46:56 +08:00
27 changed files with 421 additions and 440 deletions
+2 -1
View File
@@ -3455,7 +3455,8 @@ common_params_context common_params_parser_init(common_params & params, llama_ex
{"--reasoning-format"}, "FORMAT",
"controls whether thought tags are allowed and/or extracted from the response, and in which format they're returned; one of:\n"
"- none: leaves thoughts unparsed in `message.content`\n"
"- deepseek: puts thoughts in `message.reasoning_content` (except in streaming mode, which behaves as `none`)\n"
"- deepseek: puts thoughts in `message.reasoning_content`\n"
"- deepseek-legacy: keeps `<think>` tags in `message.content` while also populating `message.reasoning_content`\n"
"(default: auto)",
[](common_params & params, const std::string & value) {
params.reasoning_format = common_reasoning_format_from_name(value);