Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/build-apple.yml
#	.github/workflows/build-self-hosted.yml
#	.github/workflows/release.yml
#	SECURITY.md
#	build-xcframework.sh
#	ci/run.sh
#	docs/development/HOWTO-add-model.md
#	examples/model-conversion/scripts/causal/convert-model.sh
#	examples/model-conversion/scripts/embedding/convert-model.sh
#	scripts/sync_vendor.py
#	scripts/ui-assets.cmake
#	tests/test-arg-parser.cpp
#	tests/test-backend-sampler.cpp
#	tests/test-grammar-parser.cpp
#	tests/test-llama-archs.cpp
#	tests/test-sampling.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/mtmd/CMakeLists.txt
#	tools/mtmd/mtmd.h
#	tools/mtmd/tests/test-deepseek-ocr.py
#	tools/server/README.md
#	tools/tts/CMakeLists.txt
#	tools/tts/convert_pt_to_hf.py
This commit is contained in:
Concedo
2026-08-07 20:46:56 +08:00
125 changed files with 7633 additions and 2869 deletions
+1 -4
View File
@@ -5669,10 +5669,7 @@ generation_outputs gpttype_generate(const generation_inputs inputs)
std::vector<int> media_intro; //added before media list
std::vector<int> media_outro; //added before media list
std::string intro = "\nAttached Media:\n";
// if(mtmd_ctx && kcpp_mtmd_is_gemma4uv(mtmd_ctx)) //ugly fix for gemma4uv vision coherency
// {
// intro = "\n<|channel><channel|>" + intro;
// }
TokenizeString(intro, media_intro, file_format, false);
//clear previous run media memory, just-in-time free