Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/build-webgpu.yml
#	CMakeLists.txt
#	common/CMakeLists.txt
#	docs/development/HOWTO-add-model.md
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-sycl/CMakeLists.txt
#	tests/test-arg-parser.cpp
#	tests/test-jinja.cpp
#	tests/test-llama-archs.cpp
#	tests/test-save-load-state.cpp
#	tools/cli/README.md
#	tools/completion/README.md
#	tools/llama-bench/llama-bench.cpp
#	tools/mtmd/CMakeLists.txt
#	tools/server/README.md
This commit is contained in:
Concedo
2026-07-27 22:28:38 +08:00
74 changed files with 2516 additions and 361 deletions
+18 -3
View File
@@ -463,6 +463,13 @@ struct mtmd_context {
img_end = "<|vision_end|>";
image_preproc = std::make_unique<mtmd_image_preprocessor_dyn_size>(ctx_v);
} break;
case PROJECTOR_TYPE_MINIMAX_M3:
{
// ]<]start of image[>[ ... (image embeddings) ... ]<]end of image[>[
img_beg = "]<]start of image[>[";
img_end = "]<]end of image[>[";
image_preproc = std::make_unique<mtmd_image_preprocessor_dyn_size>(ctx_v);
} break;
case PROJECTOR_TYPE_YOUTUVL:
{
// <|vision_start|> ... (image embeddings) ... <|vision_end|>
@@ -555,9 +562,17 @@ struct mtmd_context {
} break;
case PROJECTOR_TYPE_KIMIK25:
{
// <|media_begin|> ... (image embeddings) ... <|media_end|>
img_beg = "<|media_begin|>";
img_end = "<|media_end|>";
// GLM-5.2-V reuses the Kimi-K2.5 vision encoder and projector, but marks
// images with its own tokens, so decide based on the text model vocab
if (lookup_token("<|begin_of_image|>") != LLAMA_TOKEN_NULL) {
// <|begin_of_image|> ... (image embeddings) ... <|end_of_image|>
img_beg = "<|begin_of_image|>";
img_end = "<|end_of_image|>";
} else {
// <|media_begin|> ... (image embeddings) ... <|media_end|>
img_beg = "<|media_begin|>";
img_end = "<|media_end|>";
}
image_preproc = std::make_unique<mtmd_image_preprocessor_dyn_size>(ctx_v);
} break;
case PROJECTOR_TYPE_LIGHTONOCR: